rewirebio.iobenchmarks
Collection coverage

Benchmark results and remaining gaps

See which pages have checked results and charts, and which still need their published evidence collected.

Release 2026-11-21-adc15377fab2. Counts include results reached through source-backed membership links. A metric row is not an independent experiment. Charts keep a source, protocol, dataset and metric together.

Pages without results indicate gaps in this collection. A paper may contain experiments we have not yet transcribed. We do not substitute unrelated results or zero scores for missing evidence.

Download the complete audit (JSON) (gzip)

Benchmarks

126 pages · 57 with results · 38 with charts.

PageEvaluations and metric rowsChartsCollection status
AlphaFold and ESMFold benchmark on PDB structures released 2022 to 20240 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
ATOM3D57 evaluations · 57 rows14 source-scoped figuresChecked result tables available.
Scope and remaining work
  • complete comparable numeric result batch: Specific candidate tables and protocol boundaries are documented; no graph values or incomplete winner-only selection are converted into publishable rows.
BacBench0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BEACON221 evaluations · 221 rows13 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Multi-task suite; model adaptation and metric differ by task. Full comparison table extraction remains pending; no composite RNA score inferred.
BEELINE384 evaluations · 588 rows71 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Primary XML has no numeric table-wrap results; comparisons are figures and supplementary data. Exact full model-by-dataset scores require supplemental/source-data extraction, not digitizing figure heights.
BenchBench-Cloning24 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BenchBench-Cloning construct-design set24 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BenchBench-Cloning protocol-development set56 evaluations · 56 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEND169 evaluations · 169 rows7 source-scoped figuresChecked result tables available.
Scope and remaining work
  • complete comparable numeric result batch: Specific candidate tables and protocol boundaries are documented; no graph values or incomplete winner-only selection are converted into publishable rows.
Benet-Pages 2025 BRCA1/BRCA2 VUS reclassification study2 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BERTax taxonomic classification of genome fragments (Mock et al. 2022)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BioML-bench0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Brandes et al. 2023 clinical missense pathogenicity benchmarks (ClinVar and HGMD/gnomAD)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Brandes et al. 2023 ClinVar in-frame indel and stop-gain pathogenicity benchmarks0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
CACHE Challenge #30 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
CAFA438 evaluations · 438 rows6 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Main tables describe participation and benchmark construction; numerical performance is mainly in figures/supplementary files. CAFA versions, ontology branch, full/partial mode and no/limited-knowledge cohorts must remain separate. No scores estimated from plot pixels.
CAMI16 evaluations · 256 rows16 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Main Table 1 gives best-ranked software, not a complete numerical score table. Assembly, genome binning, taxonomic binning and taxonomic profiling are separate tasks; strain diversity and sample cohorts must be separated. Further source-data extraction remains before new score publication.
Cancer Immunotherapy Data Science Challenge54 evaluations · 54 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CAPRI100 evaluations · 400 rows16 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Round 54 has 37 targets and 38 assessment units; round 57 has 34 targets and 47 units. These are different denominators.
  • Official page says data may change; pin each round CSV before numerical ingestion.
  • Freshly discovered Rosetta CAPRI rounds 47–55 paper (PMC12462888) was blocked: Europe PMC HTTP 500 and PMC browser challenge. It is not a universal all-participant assessment.
CASP90 evaluations · 270 rows6 source-scoped figuresChecked result tables available.
Scope and remaining work
  • complete comparable numeric result batch: Specific candidate tables and protocol boundaries are documented; no graph values or incomplete winner-only selection are converted into publishable rows.
CASP16 binding affinity challenge0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
CIViC MCP 2026 evidence-retrieval evaluation3 evaluations · 162 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ClinBench (Blank Bio)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
ClinGen SVI calibration of computational predictors for PP3/BP40 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
ClusPro Protein Docking Benchmark 5.0 study16 evaluations · 111 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DART-Eval316 evaluations · 316 rows23 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Regulatory sequence detection, TF motifs, cell-type activity and variant effects are distinct protocols. Enhancer broad-task record must link concrete tasks, not inherit every DART result. Existing DART observations require source-cell identity reuse.
Davis and KIBA drug-target affinity benchmark (DeepDTA split)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
DeepProtein benchmark0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
DEKOIS 2.00 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Differential expression classification benchmark for perturbation models (Sun et al. 2026)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
DNALONGBENCH0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
DUD-E (Directory of Useful Decoys, Enhanced)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
ENIGMA 2024 BRCA evidence-calibration and curation study5 evaluations · 39 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ESMFold2 Runs N’ Poses comparison11 evaluations · 11 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Evo 2 7B on BRCA1 saturation genome editing SNVs across cloud GPUs (Rewire, evo2-cloud-operations)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Evo 2 paper zero-shot human variant effect evaluations (Brixi et al. 2026)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
FLIP155 evaluations · 155 rows15 source-scoped figuresChecked result tables available.
Scope and remaining work
  • No suite-wide raw score. Random splits and biologically motivated splits are distinct.
  • Thermostability NA entries are not zeros; Table 4 includes negative Spearman correlations.
  • No new numeric extraction in this scoped release; full tables identified.
FLIP2149 evaluations · 293 rows33 source-scoped figuresChecked result tables available.
Scope and remaining work
  • complete comparable numeric result batch: Specific candidate tables and protocol boundaries are documented; no graph values or incomplete winner-only selection are converted into publishable rows.
FoldBench45 evaluations · 175 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FramePool translation-prediction study30 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Gene-MTEB80 evaluations · 80 rows16 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GENEB22 evaluations · 22 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Broad benchmark suite with task-specific cohorts and adaptations. Main artifact acquired; complete per-task table and supplement extraction remains pending.
GENEB leaderboard0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
GeneRNIB0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Genie 3 unconditional short monomer comparison13 evaluations · 65 rows5 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Genomic Benchmarks18 evaluations · 36 rows18 source-scoped figuresChecked result tables available.
Scope and remaining work
  • The two implementations are not distinct foundation-model families.
  • Dataset totals in Table 1 are not test-set denominators.
  • Table 2 does not enumerate dataset-version numbers, split file hashes or replicate uncertainty.
GFMBench-API0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
GlycanML323 evaluations · 323 rows50 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Paper table does not enumerate trained checkpoint hashes; source configuration names retained.
GPCRrecent0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
GPN paper: Arabidopsis thaliana held-out sequence modelling and embedding evaluation0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
GPN paper: unsupervised variant effect prediction in Arabidopsis thaliana0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
GPN-MSA variant effect prediction evaluation (Benegas et al.)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
GPN-Star variant effect prediction benchmarks (Ye et al. 2026)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
GUANinE v1.10 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
GUE280 evaluations · 280 rows28 source-scoped figuresChecked result tables available.
Scope and remaining work
  • complete comparable numeric result batch: Specific candidate tables and protocol boundaries are documented; no graph values or incomplete winner-only selection are converted into publishable rows.
Harmonised single-cell and spatial foundation model benchmark (Chen et al. 2026)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
HECTOR 2026 preprint: ENIGMA Evidence Repository validation1 evaluation · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HEST-Benchmark100 evaluations · 100 rows10 source-scoped figuresChecked result tables available.
Scope and remaining work
  • New web search finds updated official benchmark inventory; current README values cannot be assigned to original v 1 paper configurations. Fresh PDF retrieval failed; cached pinned v 1 PDF preserved. Complete table extraction remains pending.
Hu 2026 BRCA2 integrated functional-data classification study1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HyCell report benchmark on seven held-out atlases0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
HyInv technical report inverse-folding comparison0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
HyPLM technical report protein language model evaluation0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Jores plant promoter prediction study4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
LiPP benchmark set0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
LIT-PCBA0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Livesey and Marsh variant effect predictor benchmark (2025 edition)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Ludaic and Elofsson 2026 RNA structure benchmark0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
M. tuberculosis read classification with standard and custom databases (Hall and Coin 2024)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
MassSpecGym24 evaluations · 116 rows28 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
MetageNN long-read genus classification benchmark (Peres da Silva et al. 2024)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
MF-PCBA0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
MIST CANOPUS molecular retrieval6 evaluations · 45 rows8 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Mock community taxonomic profiling benchmark (Portik et al. 2022)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
MPRabc K562 enhancer–gene evaluation6 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
mRNABench696 evaluations · 700 rows26 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Table 5 labels localization columns Pearson R while Table 2 labels them AUPRC; quarantine those metric identities pending reconciliation.
  • Appendix C claims ten splits but enumerates nine seeds. Record ten as reported, with discrepancy, not an inferred tenth seed.
  • Tables 5–6 uncertainties are 95% confidence intervals, not standard deviations.
  • Task/subtask pooling and transformed aggregate rankings must not be conflated with printed raw metrics.
MSAlign molecular retrieval evaluations63 evaluations · 189 rows24 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench1,101 evaluations · 1,101 rows43 source-scoped figuresChecked result tables available.
Scope and remaining work
  • complete comparable numeric result batch: Specific candidate tables and protocol boundaries are documented; no graph values or incomplete winner-only selection are converted into publishable rows.
Nucleotide Transformer benchmark (18 tasks)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
OncoVI 2026 oncogenicity evaluation study5 evaluations · 27 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Open Problems384 evaluations · 384 rows24 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Task release, dataset, preprocessing and metric must be fixed before charting.
  • The page lists multiple releases; a downloaded release artifact is needed to pin exact numerical leaderboard observations.
  • No values estimated from chart coordinates.
PepSpecBench0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Perturbation-target prediction from attention-derived edge scores (Kendiukhov 2026, Objective B)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
PerturBench76 evaluations · 76 rows8 source-scoped figuresChecked result tables available.
Scope and remaining work
  • complete comparable numeric result batch: Specific candidate tables and protocol boundaries are documented; no graph values or incomplete winner-only selection are converted into publishable rows.
PEtab benchmark collection0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • Collection of parameter-estimation problems, not one universal biological accuracy benchmark. Model/dataset identifiers, objective, solver and restart budget are necessary before comparing runs. No universal score generated.
PFMBench141 evaluations · 141 rows12 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Core-model filtering and excluded poorly performing tasks make Table 3 a selected subset, not all 17 models across every task.
  • Task metrics and 30% sequence-identity splits vary; Table 1 maps each.
  • Full values staged only after task-specific extraction; no overall family ranking inferred.
PLABench0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Plant Genomic Benchmark (PGB)24 evaluations · 24 rows12 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Plasma mcfDNA sequencing for predicting and diagnosing bloodstream infection in high-risk leukaemia (Wolf et al. 2026)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
PLINDER7 evaluations · 33 rows5 source-scoped figuresChecked result tables available.
Scope and remaining work
  • complete comparable numeric result batch: Specific candidate tables and protocol boundaries are documented; no graph values or incomplete winner-only selection are converted into publishable rows.
POISK co-folding binder-versus-decoy benchmark0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
PRIME viral mutation-space evaluation0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Protein embeddings for GNN PPI prediction (OGBl-ppa and HuRI)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
ProteinBench556 evaluations · 556 rows95 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Mean/median slash pairs in Table 7 are not uncertainty.
  • EigenFold removes unknown amino acids and lacks a peptide-bond metric; preserve applicability caveats.
  • Do not transfer Table 8 bootstrap uncertainty to Table 7.
ProteinGym284 evaluations · 2,074 rows17 source-scoped figuresChecked result tables available.
Scope and remaining work
  • complete comparable numeric result batch: Specific candidate tables and protocol boundaries are documented; no graph values or incomplete winner-only selection are converted into publishable rows.
Public binding free energy benchmark (Ross et al. 2023)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
RFD4-Proteina frozen project benchmark, October 9 2026 supplement0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
RhoFold+ CASP15 natural RNA comparison56 evaluations · 112 rows12 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
RhoMax original wavelength-prediction comparison15 evaluations · 60 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
RNAGym fitness leaderboard v0.1.10 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Scaffold-Lab unconditional generation0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
scFoundation cell-type annotation comparison14 evaluations · 14 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Sci-Plex highest-dosage holdout benchmark (GIM protocol)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
scIB69 evaluations · 821 rows13 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Bio-conservation and batch-removal components depend on datasets and preprocessing. Figures do not justify new exact numerical scores; official source-data matrix extraction remains pending. Broad batch integration is not identical to scIB or Open Problems.
SCMBench0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
scTab published annotation evaluation21 evaluations · 26 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation294 evaluations · 588 rows28 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SEQC2 HCC1395 somatic CNV benchmark0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Short-read versus host-depleted nanopore mNGS on BALF (Hu et al. 2026)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
So 2024 BRCA1 ClinVar conflicting-variant reinterpretation study1 evaluation · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Static GRN reconstruction from single-cell foundation models (Ye et al. 2026)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Talos 2026 evaluation and reanalysis study14 evaluations · 82 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TAPE50 evaluations · 50 rows5 source-scoped figuresChecked result tables available.
TDC molecular tasks66 evaluations · 66 rows22 source-scoped figuresChecked result tables available.
Scope and remaining work
  • complete comparable numeric result batch: Specific candidate tables and protocol boundaries are documented; no graph values or incomplete winner-only selection are converted into publishable rows.
  • Fresh arXiv v1 retrieval was incomplete and primary NSF v2 retrieval timed out; cached v1 bytes were hash-verified. The v2 full text is not claimed to have been reviewed.
TorchCraft 10-ligand pocket design benchmark0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
TorchCraft 12-target minibinder design benchmark0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
TorchCraft 15-target VHH design benchmark0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
TorchCraft 8-target cyclic peptide design benchmark0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
TorchCraft runtime benchmark across sequence lengths0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
TraitGym0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Universal antibody-antigen affinity evaluation on AlphaBind (MochiBind study)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
ViroBench0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Virtual Cell Challenge 20261,048 evaluations · 1,048 rows14 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Challenge scope found; this pass does not establish a final published 2026 result table. Do not copy 2025 rankings into 2026 challenge.
Virus profiler benchmark against a shared Virus Pathogen Database (Tisza et al. 2026)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Zero-shot cell embedding evaluation of single-cell foundation models (Kedzierska et al. 2025)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Zero-shot RNA language model benchmark (Wang et al. 2026)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.

Tasks

552 pages · 488 with results · 389 with charts.

PageEvaluations and metric rowsChartsCollection status
A-to-I RNA editing site prediction1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • This is validation-set reporting, not a cleanly identified untouched test set.
  • Table 2 calls it the '15% liver validation set', while methods describe held-out 20% validation; retain wording and resolve data partition before external ranking.
  • No uncertainty in the table.
antibody deamidation-site prediction1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
Antibody loop structure prediction2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Complete raw table acquired. Antibodyloops cannot be pooled withnanobody/TCR cohorts orframeworkRMSD; sixloopregions separate. LowerÅRMSD; nanobodylight-chain N/A retained. Structured extraction pending.
Antibody–antigen interaction prediction using folded complexes2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Original structure 0.89 ± 0.05 spans columns and is one reference result, not three independent results.
  • Table 3 XML merges three RMSD cells using ampersands; numeric normalization needs explicit splitting/visual check.
  • Confidence pTM/ipTM is not experimental interaction accuracy.
antigen-antibody HIV neutralization prediction1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Keep the three held-out-entity regimes separate. Section S1 contains detailed split/hyperparameter information; no sequence-design or biological optimization material is part of this extraction.
ATOM3D LBA-RMSE: Ligand binding affinity, root mean squared error5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ATOM3D LBA-RP: Ligand binding affinity, global Pearson correlation5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ATOM3D LBA-RS: Ligand binding affinity, global Spearman correlation5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ATOM3D LEP-AUROC: Ligand efficacy prediction4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ATOM3D MSP: Mutation stability prediction4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ATOM3D PIP: Protein interface prediction3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ATOM3D PSR-GLOBAL-RS: Protein structure ranking, global Spearman3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ATOM3D PSR-MEAN-RS: Protein structure ranking, mean Spearman within a target3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ATOM3D RES: Residue identity4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ATOM3D RSR-GLOBAL-RS: RNA structure ranking, global Spearman3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ATOM3D RSR-MEAN-RS: RNA structure ranking, mean Spearman within a target3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ATOM3D SMP-EGAP: Small molecule properties, HOMO-LUMO gap5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ATOM3D SMP-MU: Small molecule properties, dipole moment5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ATOM3D SMP-U0AT: Small molecule properties, atomization energy5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BacBench Antibiotic resistance prediction0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BacBench Essential gene prediction0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BacBench Operon identification from long-read RNA sequencing0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BacBench Phenotypic trait prediction0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BacBench Protein-protein interaction prediction0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BacBench Strain clustering0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Bacterial promoter prediction0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • Broad bacterial promoter prediction includes other organisms and dataset constructions; one E. coli table is not a universal ranking.
Batch integration0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • Bio-conservation and batch-removal components depend on datasets and preprocessing. Figures do not justify new exact numerical scores; official source-data matrix extraction remains pending. Broad batch integration is not identical to scIB or Open Problems.
BEACON APA: Alternative polyadenylation isoform prediction17 evaluations · 17 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEACON CMP: Contact map prediction17 evaluations · 17 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEACON CRI-Off: CRISPR off-target effect prediction17 evaluations · 17 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEACON CRI-On: CRISPR on-target efficiency prediction17 evaluations · 17 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEACON DMP: Distance map prediction17 evaluations · 17 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEACON Modif: RNA modification site prediction17 evaluations · 17 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEACON MRL: Mean ribosome loading prediction17 evaluations · 17 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEACON ncRNA: Non-coding RNA family classification17 evaluations · 17 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEACON PRS: Programmable RNA switch prediction17 evaluations · 17 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEACON SPL: Splice site prediction17 evaluations · 17 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEACON SSI: Structure score imputation17 evaluations · 17 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEACON SSP: Secondary structure prediction17 evaluations · 17 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEACON VDP: Vaccine degradation prediction17 evaluations · 17 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BenchBench-Cloning construct design: AG/AP1 chimera plasmid8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BenchBench-Cloning construct design: Alkaloid-pathway GoldenBraid set8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BenchBench-Cloning construct design: Detector choice from antibody data8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BenchBench-Cloning construct design: Dual-luciferase frame panel8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BenchBench-Cloning construct design: GFP into EcoFlex vector8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BenchBench-Cloning construct design: Insulin intermediate construct8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BenchBench-Cloning construct design: Insulin two-chain constructs8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BenchBench-Cloning construct design: Matched promoter panel8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BenchBench-Cloning construct design: Minimal-edit recoding8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BenchBench-Cloning construct design: MPRA construct rebuild8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BenchBench-Cloning construct design: Prime-assembly donor family8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BenchBench-Cloning construct design: Reporter choice from data8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BenchBench-Cloning construct design: Sodium-channel promoter repair8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BenchBench-Cloning construct design: Synthetic-chromosome locus edit8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BenchBench-Cloning construct design: Tus/TerB HEK293 constructs8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEND CHROMATIN: Chromatin accessibility23 evaluations · 23 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEND CPG: CpG methylation24 evaluations · 24 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEND ENHANCER: Enhancer annotation25 evaluations · 25 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEND GENE-FINDING: Gene finding25 evaluations · 25 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEND HISTONE: Histone modification24 evaluations · 24 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEND VARIANT-DISEASE: Noncoding variant effects on disease24 evaluations · 24 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEND VARIANT-EXPRESSION: Noncoding variant effects on expression24 evaluations · 24 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BioML-bench task CBX4_HUMAN_multi-sub0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BioML-bench task CSN4_MOUSE_indels0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BioML-bench task open-problems-cell-communication0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BioML-bench task open-problems-label-projection0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BioML-bench task open-problems-modality0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BioML-bench task open-problems-perturbations0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BioML-bench task open-problems-spatial-genes0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BioML-bench task polaris-adme-fang-hclint-10 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BioML-bench task polaris-adme-fang-hppb-10 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BioML-bench task polaris-adme-fang-solu-10 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BioML-bench task polaris-pkis2-egfr-wt-c-10 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BioML-bench task PSAE_PICP2_indels0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BioML-bench task Q8EG35_SHEON_indels0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BioML-bench task SPA_STAAU_Tsuboyama_20230 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BioML-bench task SPIKE_SARS2_Starr_20200 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BioML-bench task tdcommons-bbb-martins0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BioML-bench task tdcommons-caco2-wang0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BioML-bench task tdcommons-cyp2d6-substrate0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BioML-bench task tdcommons-herg0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BioML-bench task tdcommons-lipophilicity0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Biomolecular complex structure0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • complete comparable numeric result batch: Specific candidate tables and protocol boundaries are documented; no graph values or incomplete winner-only selection are converted into publishable rows.
CAMI genome binning0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • Main Table 1 gives best-ranked software, not a complete numerical score table. Assembly, genome binning, taxonomic binning and taxonomic profiling are separate tasks; strain diversity and sample cohorts must be separated. Further source-data extraction remains before new score publication.
CAMI II phylum read classification1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Table 5 prints NCD only. Narrative compares Kraken2 but supplies no paired numerical Kraken2 row; do not manufacture a two-model chart.
  • Do not attach five-fold Human DNA results from Table 3 to CAMI II.
CAMI II superkingdom read classification1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Table 5 prints NCD only. Narrative compares Kraken2 but supplies no paired numerical Kraken2 row; do not manufacture a two-model chart.
  • Do not attach five-fold Human DNA results from Table 3 to CAMI II.
CAMI metagenome assembly0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • Main Table 1 gives best-ranked software, not a complete numerical score table. Assembly, genome binning, taxonomic binning and taxonomic profiling are separate tasks; strain diversity and sample cohorts must be separated. Further source-data extraction remains before new score publication.
CAMI taxonomic binning0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • Main Table 1 gives best-ranked software, not a complete numerical score table. Assembly, genome binning, taxonomic binning and taxonomic profiling are separate tasks; strain diversity and sample cohorts must be separated. Further source-data extraction remains before new score publication.
CAMI taxonomic profiling0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • Main Table 1 gives best-ranked software, not a complete numerical score table. Assembly, genome binning, taxonomic binning and taxonomic profiling are separate tasks; strain diversity and sample cohorts must be separated. Further source-data extraction remains before new score publication.
CATH superfamily annotation1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
cell-type annotation1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
Cell-type annotation2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
Cell-type deconvolution of bulk RNA-seq with single-cell references0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Cell-type identification2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
Cell-type structure in frozen embeddings2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
clathrin protein classification14 evaluations · 79 rows6 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
Clinical missense variant pathogenicity classification0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
ClinVar 3-prime UTR variant classification1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Complete raw matrix acquired. Five methods for assignedUTRrow; othervariantclasses remain separate. Alignment-aware versus sequence-only inputs explicit; no architecture equivalence inferred. Structured extraction pending.
Combinatorial cell-label classification2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Partial-credit and full-label metrics cannot share a ranking; keep dataset and label regime explicit.
  • Version is the archived preprint, not a later model family release.
Community profiling0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • OPAL is an evaluator rather than a single dataset. Numerical comparisons require selected community dataset, taxonomic rank and profiling output version. No complete main-text score matrix; source data remains pending.
Cross-dataset single-cell drug response transfer2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Keep bulk and single-cell settings explicit; do not call this feature-unseen inductive transfer.
  • Standard deviations are printed; resolve exact aggregation population from scenario-level source data before attaching seed-count error bars.
Cross-platform scATAC cell-type annotation2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Reference-to-query direction is part of protocol identity; reversed pairs are not replicates.
  • Inputs and adaptation differ across baselines; scJoint uses scATAC at both stages and Cellcano follows its original target-size-dependent rounds.
  • No uncertainty in tables; F1 and accuracy printed separately, including slash-joined Table 3 cells.
cross-species conservation prediction1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Table 1 is not a complete baseline comparison: named full-baseline scores are in Fig. 2/source workbook. Do not invent model identities from 'best benchmark'.
  • Keep lower PlantCAD2 non-TIS score as printed.
Cyclic peptide design against a protein target0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
DART-Eval CA-AUROC-GM12878: Chromatin activity prediction, GM12878, positives against negatives13 evaluations · 13 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DART-Eval CA-AUROC-H1ESC: Chromatin activity prediction, H1ESC, positives against negatives13 evaluations · 13 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DART-Eval CA-AUROC-HEPG2: Chromatin activity prediction, HEPG2, positives against negatives13 evaluations · 13 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DART-Eval CA-AUROC-IMR90: Chromatin activity prediction, IMR90, positives against negatives13 evaluations · 13 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DART-Eval CA-AUROC-K562: Chromatin activity prediction, K562, positives against negatives13 evaluations · 13 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DART-Eval CA-SPEARMAN-GM12878: Chromatin activity prediction, GM12878, positives only13 evaluations · 13 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DART-Eval CA-SPEARMAN-H1ESC: Chromatin activity prediction, H1ESC, positives only13 evaluations · 13 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DART-Eval CA-SPEARMAN-HEPG2: Chromatin activity prediction, HEPG2, positives only13 evaluations · 13 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DART-Eval CA-SPEARMAN-IMR90: Chromatin activity prediction, IMR90, positives only13 evaluations · 13 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DART-Eval CA-SPEARMAN-K562: Chromatin activity prediction, K562, positives only13 evaluations · 13 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DART-Eval CTS-ACC: Cell-type-specific element classification, overall accuracy14 evaluations · 14 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DART-Eval CTS-GM12878: Cell-type-specific element classification, GM1287814 evaluations · 14 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DART-Eval CTS-H1ESC: Cell-type-specific element classification, H1ESC14 evaluations · 14 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DART-Eval CTS-HEPG2: Cell-type-specific element classification, HEPG214 evaluations · 14 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DART-Eval CTS-IMR90: Cell-type-specific element classification, IMR9014 evaluations · 14 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DART-Eval CTS-K562: Cell-type-specific element classification, K56214 evaluations · 14 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DART-Eval REI-ABS: Regulatory element identification, absolute accuracy13 evaluations · 13 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DART-Eval REI-ACC: Regulatory element identification, zero-shot accuracy6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DART-Eval REI-PAIR: Regulatory element identification, paired accuracy13 evaluations · 13 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DART-Eval VS-AFRICAN-AUROC: Variant scoring on Chromatin QTLs in African LCLs, AUROC22 evaluations · 22 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DART-Eval VS-AFRICAN-PEARSON_R: Variant scoring on Chromatin QTLs in African LCLs, Pearson r13 evaluations · 13 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DART-Eval VS-YORUBAN-AUROC: Variant scoring on DNase QTLs in Yoruban LCLs, AUROC22 evaluations · 22 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DART-Eval VS-YORUBAN-PEARSON_R: Variant scoring on DNase QTLs in Yoruban LCLs, Pearson r13 evaluations · 13 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
De novo minibinder design against a protein target0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
differentially expressed gene identification1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Do not pool cell types or recall thresholds; table gives no uncertainty for these cells.
Discriminating antibody binders from sequence-similar putative non-binders0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
DNA-binding residue prediction1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Complete raw table acquired. Assigned benchmark is DNA-binding; RNA cohorts need distinct protocols. PCC-to-MegSite agreement and associatedPvalues are not predictive performance. Structured extraction pending.
Donor-aware age-class prediction2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Complete raw comparison acquired. Best-scFM is a selected pipeline, not a named family by inference. PCA, permutation mean/p 95 and chance 1/K remain separate reference types. Structured extraction pending.
Donor-held-out reference mapping0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • A split by batch/reference is not automatically a donor-held-out split. A chart needs the exact dataset donor manifest.
  • Open Problems controls and normalization choices must remain separate from raw label accuracy/F1.
E. coli sigma70 promoter prediction15 evaluations · 60 rows4 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
E. coli sigma70 promoter prediction2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
Enhancer / MPRA effects0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • Regulatory sequence detection, TF motifs, cell-type activity and variant effects are distinct protocols. Enhancer broad-task record must link concrete tasks, not inherit every DART result. Existing DART observations require source-cell identity reuse.
Enhancer classification2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
enhancer prediction1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Text S6 defines the independent test set; supplementary data is necessary for a complete dataset manifest.
  • Table 2 does not report replicate uncertainty; other-method provenance must retain paper citations rather than imply all were rerun.
enhancer prediction1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Published Fig. 5/6 advanced-model comparisons require figure/source-data review; do not pretend Table 3 gives scores.
  • Avoid mixing human and mouse populations or treating source-level similarity filtering as an exact split manifest.
enhancer recognition1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
Enhancer-target gene prediction2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
Enzyme functional identity prediction5 evaluations · 40 rows8 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
extremely long RNA species classification1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • No uncertainty in Table 2; exact long-sequence window/aggregation details remain tied to this paper's downstream classifiers.
  • Species classification scores do not measure RNA-structure accuracy.
FLIP AAV-1-VS-REST: AAV fitness prediction, 1-vs-rest split12 evaluations · 12 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP AAV-2-VS-REST: AAV fitness prediction, 2-vs-rest split12 evaluations · 12 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP AAV-7-VS-REST: AAV fitness prediction, 7-vs-rest split12 evaluations · 12 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split9 evaluations · 9 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP AAV-LOW-VS-HIGH: AAV fitness prediction, low-vs-high split12 evaluations · 12 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP AAV-MUT-DES: AAV fitness prediction, Mut-Des split12 evaluations · 12 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP GB1-1-VS-REST: GB1 fitness prediction, 1-vs-rest split13 evaluations · 13 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP GB1-2-VS-REST: GB1 fitness prediction, 2-vs-rest split13 evaluations · 13 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP GB1-3-VS-REST: GB1 fitness prediction, 3-vs-rest split13 evaluations · 13 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP GB1-LOW-VS-HIGH: GB1 fitness prediction, low-vs-high split13 evaluations · 13 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP RANDOM-SAMPLED-SPLITS-AAV: Random sampled splits fitness prediction, AAV split5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP RANDOM-SAMPLED-SPLITS-GB1: Random sampled splits fitness prediction, GB1 split5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP THERMOSTABILITY-HUMAN-CELL: Thermostability fitness prediction, Human-Cell split8 evaluations · 8 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP THERMOSTABILITY-HUMAN: Thermostability fitness prediction, Human split8 evaluations · 8 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP THERMOSTABILITY-MIXED: Thermostability fitness prediction, Mixed split8 evaluations · 8 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
flu-vaccine mRNA property prediction1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
Framework-conditioned VHH design against a protein target0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
G-quadruplex classification2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Complete raw tables acquired. Positive/negative construction, sequence lengths and train/test splits remain part of each G4 protocol; existing observations preserved. Structured extraction pending.
gene fusion breakpoint classification1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Counts are approximate (~36k train, ~8k validation, ~8k test) and must remain approximate.
  • NN values are final-epoch performance; SVM is a single run. No replicate confidence bounds.
  • Do not assign embedding-plus-classifier scores to bare foundation-model checkpoints.
Gene-regulatory link prediction2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Raw XML stacked AUROC/AUPRC cells preserved with explicit linebreak delimiters. Two GENELink settings must not be conflated. Structured table extraction and exact uncertainty scope remain pending.
gene-regulatory signal prediction1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Original asymmetric extraction in Table 4 is not a fair matched-input comparison; prefer Table 9 with its single-seed context.
  • Strict leave-both-out improvements shrink near zero; do not omit this limitation.
  • Source contains rounded deltas and intervals/significance annotations; do not recompute them from rounded absolute numbers.
GENEB LINEAR-PROBE: Average macro-MCC across the 13 representative tasks, linear probe11 evaluations · 11 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GENEB MLP-PROBE: Average macro-MCC across the 13 representative tasks, MLP probe11 evaluations · 11 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Genome-wide prophage detection17 evaluations · 102 rows6 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
Genomic Benchmarks DEMO-CODING-VS-INTERGENOMIC-SEQS-ACCURACY: demo_coding_vs_intergenomic_seqs, Accuracy2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Genomic Benchmarks DEMO-CODING-VS-INTERGENOMIC-SEQS-F1: demo_coding_vs_intergenomic_seqs, F1 score2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Genomic Benchmarks DEMO-HUMAN-OR-WORM-ACCURACY: demo_human_or_worm, Accuracy2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Genomic Benchmarks DEMO-HUMAN-OR-WORM-F1: demo_human_or_worm, F1 score2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Genomic Benchmarks DROSOPHILA-ENHANCERS-STARK-ACCURACY: drosophila_enhancers_stark, Accuracy2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Genomic Benchmarks DROSOPHILA-ENHANCERS-STARK-F1: drosophila_enhancers_stark, F1 score2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Genomic Benchmarks DUMMY-MOUSE-ENHANCERS-ENSEMBL-ACCURACY: dummy_mouse_enhancers_ensembl, Accuracy2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Genomic Benchmarks DUMMY-MOUSE-ENHANCERS-ENSEMBL-F1: dummy_mouse_enhancers_ensembl, F1 score2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Genomic Benchmarks HUMAN-ENHANCERS-COHN-ACCURACY: human_enhancers_cohn, Accuracy2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Genomic Benchmarks HUMAN-ENHANCERS-COHN-F1: human_enhancers_cohn, F1 score2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Genomic Benchmarks HUMAN-ENHANCERS-ENSEMBL-ACCURACY: human_enhancers_ensembl, Accuracy2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Genomic Benchmarks HUMAN-ENHANCERS-ENSEMBL-F1: human_enhancers_ensembl, F1 score2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Genomic Benchmarks HUMAN-ENSEMBL-REGULATORY-ACCURACY: human_ensembl_regulatory, Accuracy2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Genomic Benchmarks HUMAN-ENSEMBL-REGULATORY-F1: human_ensembl_regulatory, F1 score2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Genomic Benchmarks HUMAN-NONTATA-PROMOTERS-ACCURACY: human_nontata_promoters, Accuracy2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Genomic Benchmarks HUMAN-NONTATA-PROMOTERS-F1: human_nontata_promoters, F1 score2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Genomic Benchmarks HUMAN-OCR-ENSEMBL-ACCURACY: human_ocr_ensembl, Accuracy2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Genomic Benchmarks HUMAN-OCR-ENSEMBL-F1: human_ocr_ensembl, F1 score2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GlycanML glycosylation type prediction10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Paper table does not enumerate trained checkpoint hashes; source configuration names retained.
GlycanML immunogenicity prediction10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Paper table does not enumerate trained checkpoint hashes; source configuration names retained.
GlycanML protein-glycan interaction prediction10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Paper table does not enumerate trained checkpoint hashes; source configuration names retained.
GlycanML taxonomy prediction190 evaluations · 190 rows26 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Paper table does not enumerate trained checkpoint hashes; source configuration names retained.
GUE CORE-PROMOTER-DETECTION-ALL: Core promoter detection, dataset all10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUE CORE-PROMOTER-DETECTION-NOTATA: Core promoter detection, dataset notata10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUE CORE-PROMOTER-DETECTION-TATA: Core promoter detection, dataset tata10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUE EPIGENETIC-MARKS-PREDICTION-H3: Epigenetic marks prediction, dataset H310 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUE EPIGENETIC-MARKS-PREDICTION-H3K14AC: Epigenetic marks prediction, dataset H3K14ac10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUE EPIGENETIC-MARKS-PREDICTION-H3K36ME3: Epigenetic marks prediction, dataset H3K36me310 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUE EPIGENETIC-MARKS-PREDICTION-H3K4ME1: Epigenetic marks prediction, dataset H3K4me110 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUE EPIGENETIC-MARKS-PREDICTION-H3K4ME2: Epigenetic marks prediction, dataset H3K4me210 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUE EPIGENETIC-MARKS-PREDICTION-H3K4ME3: Epigenetic marks prediction, dataset H3K4me310 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUE EPIGENETIC-MARKS-PREDICTION-H3K79ME3: Epigenetic marks prediction, dataset H3K79me310 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUE EPIGENETIC-MARKS-PREDICTION-H3K9AC: Epigenetic marks prediction, dataset H3K9ac10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUE EPIGENETIC-MARKS-PREDICTION-H4: Epigenetic marks prediction, dataset H410 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUE PROMOTER-DETECTION-ALL: Promoter detection, dataset all10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUE PROMOTER-DETECTION-NOTATA: Promoter detection, dataset notata10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUE PROMOTER-DETECTION-TATA: Promoter detection, dataset tata10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUE SPLICE-SITE-PREDICTION-RECONSTRUCT: Splice site prediction, dataset Reconstruct10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUE TRANSCRIPTION-FACTOR-PREDICTION-HUMAN-0: Transcription factor prediction (human), dataset 010 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUE TRANSCRIPTION-FACTOR-PREDICTION-HUMAN-1: Transcription factor prediction (human), dataset 110 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUE TRANSCRIPTION-FACTOR-PREDICTION-HUMAN-2: Transcription factor prediction (human), dataset 210 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUE TRANSCRIPTION-FACTOR-PREDICTION-HUMAN-3: Transcription factor prediction (human), dataset 310 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUE TRANSCRIPTION-FACTOR-PREDICTION-HUMAN-4: Transcription factor prediction (human), dataset 410 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUE TRANSCRIPTION-FACTOR-PREDICTION-MOUSE-0: Transcription factor prediction (mouse), dataset 010 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUE TRANSCRIPTION-FACTOR-PREDICTION-MOUSE-1: Transcription factor prediction (mouse), dataset 110 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUE TRANSCRIPTION-FACTOR-PREDICTION-MOUSE-2: Transcription factor prediction (mouse), dataset 210 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUE TRANSCRIPTION-FACTOR-PREDICTION-MOUSE-3: Transcription factor prediction (mouse), dataset 310 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUE TRANSCRIPTION-FACTOR-PREDICTION-MOUSE-4: Transcription factor prediction (mouse), dataset 410 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Held-out-clade classification0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • Table does not give uncertainty for each genus accuracy; BLAST is an alignment reference, not a pretrained encoder.
HEST-Benchmark CCRCC: Gene expression prediction from histology, Clear cell renal cell carcinoma10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HEST-Benchmark COAD: Gene expression prediction from histology, Colon adenocarcinoma10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HEST-Benchmark HCC: Gene expression prediction from histology, Hepatocellular carcinoma10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HEST-Benchmark IDC: Gene expression prediction from histology, Invasive ductal carcinoma10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HEST-Benchmark LUNG: Gene expression prediction from histology, Lung10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HEST-Benchmark LYMPH_IDC: Gene expression prediction from histology, Lymph node metastasis of invasive ductal carcinoma10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HEST-Benchmark PAAD: Gene expression prediction from histology, Pancreatic adenocarcinoma10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HEST-Benchmark PRAD: Gene expression prediction from histology, Prostate adenocarcinoma10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HEST-Benchmark READ: Gene expression prediction from histology, Rectum adenocarcinoma10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HEST-Benchmark SKCM: Gene expression prediction from histology, Skin cutaneous melanoma10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Hierarchical metagenomic taxonomy classification2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • MetaPhlAn4 uses its official prebuilt database, unlike the common training database; preserve the asterisk.
  • CAT and MetaPhlAn4 do not supply probabilities, so AveP is inapplicable, not zero.
  • Bootstrap intervals exist in supplemental figures; main-table values lack printed intervals.
Homolog-like variant generation from a seed antibody sequence0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Human 5mC detection2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
human core-promoter classification1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
human protein-protein interaction prediction1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Complete raw table acquired. HumanPPI AUC column must be extracted separately from localization, thermostability,fluorescence andGO. Different model sizes/representation inputs remain distinct. Structured extraction pending.
human RNA 2-prime-O-methylation site prediction12 evaluations · 84 rows14 source-scoped figuresChecked result tables available.
Scope and remaining work
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
Human thymus cell-type classification2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only the thymus row belongs to the assigned benchmark; cortex and breast must be separate protocols.
  • The authors' Euclidean nonidentity check is not proof that all leakage is absent; source wording must not become an independently established guarantee.
  • No replicate uncertainty in Table 4.
human-versus-viral protein classification8 evaluations · 32 rows4 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
Immunotherapy response from pretreatment bulk RNA-seq0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Intrinsically disordered protein ensemble docking2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Parenthesized numbers are the <5 Å success percentage, not uncertainty; main numbers use <3 Å.
  • Each ligand and ensemble/matching definition needs its own group; do not pool them.
  • MD-reference agreement is not experimental binding affinity.
Isoform usage recovery from gene-level expression0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Ligand potency prediction using generated poses2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
Ligand-conditioned protein pocket design0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Lipid–protein binding pose2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Complete raw tables acquired. RMSD-only versusRMSD+physicalvalidity separate;95%exactbinomialCI onLiPP, prior PoseBusters numbers quoted and notnewindependent runs. Structured extraction pending.
Long-range regulation0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • complete comparable numeric result batch: Specific candidate tables and protocol boundaries are documented; no graph values or incomplete winner-only selection are converted into publishable rows.
Long-read taxonomic profiling9 evaluations · 23 rows3 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
MassSpecGym De novo molecule generation6 evaluations · 36 rows12 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
MassSpecGym Molecule retrieval10 evaluations · 40 rows8 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
MassSpecGym Spectrum simulation8 evaluations · 40 rows8 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
Mean ribosome load from MPRA2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Table 5 labels localization columns Pearson R while Table 2 labels them AUPRC; quarantine those metric identities pending reconciliation.
  • Appendix C claims ten splits but enumerates nine seeds. Record ten as reported, with discrepancy, not an inferred tenth seed.
  • Tables 5–6 uncertainties are 95% confidence intervals, not standard deviations.
  • Task/subtask pooling and transformed aggregate rankings must not be conflated with printed raw metrics.
metagenomic genus classification1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Complete raw table acquired. Dataset and k-mer row spans must be propagated; CNN/DBN/RDP/PC-mer-LR/WalkIm rows retained. Structured extraction pending; do not infer equivalent preprocessing.
Metagenomic taxonomic classification2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Complete raw tables acquired.19 new versusold reference experiments separate; Bray-Curtis lower-is-better unlike F1. Reference database state required before chart groups. Structured extraction pending.
MFASS splice-variant prioritisation9 evaluations · 31 rows4 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Primary browser text accessible but rawXML endpoint 500, PMC HTMLreCAPTCHA and mirror returned 0 bytes. Existing MFASS corrected runs must retain identities and assay-oriented window correction; no new score duplicates or revert to withdrawn v 1 conclusion.
microbiome disease-state classification1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Disease datasets and cohort prevalences differ; do not pool accuracy.
  • No uncertainty in Table 3. Visualization using a 7:3 split is not the evaluation split.
miRNA-mRNA interaction prediction1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
Mock-community MAG taxonomy classification2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Do not pool assemblies, ranks or raw/corrected taxonomic labels.
  • Table entries such as '9 + 33' and '8 + 35' are printed decompositions, not unambiguous single numerical observations.
  • Total MAGs and metric confusion-matrix denominators differ; retain both.
Monomer structure0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • Mean and median are separate aggregates; slash pairs are not confidence bounds.
  • ESMFold Science publisher full-text request returned HTTP 403; its DOI was discovered but not used for uninspected full-text claims.
mRNA half-life prediction1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
mRNA-protein interaction prediction1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
mRNABench ECLIP: eCLIP binding site prediction21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
mRNABench GO: Gene Ontology term prediction21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
mRNABench HL: mRNA half life21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
mRNABench MRL-HL-PAIR: Paired mean ribosome load and half life21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
mRNABench MRL-MPRA: Mean ribosome load on an MPRA library21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
mRNABench MRL: Mean ribosome load21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
mRNABench MRNA-LOC-LR: mRNA localisation, long range21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
mRNABench MRNA-LOC-SR: mRNA localisation, short range21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
mRNABench PROT-LOC: Protein localisation21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
mRNABench VEP: Variant effect prediction21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Multi-species prokaryotic promoter detection2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • iPro-MP's first four scores duplicate across Tables 1–2; one result with two source occurrences.
  • Species-averaged accuracy/AUROC/AUPRC/MCC differ from pooled sample scores; retain source aggregation.
  • Runtime is seconds, lower-is-better, and hardware-dependent.
Mutated RBD binding prediction2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
NABench CCV-CORR-APTAMER: Fitness prediction on aptamer assays, supervised, contiguous cross validation25 evaluations · 25 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench CCV-CORR-ENHANCER: Fitness prediction on enhancer assays, supervised, contiguous cross validation25 evaluations · 25 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench CCV-CORR-MRNA: Fitness prediction on mRNA assays, supervised, contiguous cross validation25 evaluations · 25 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation23 evaluations · 23 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench CCV-CORR-RIBOZYME: Fitness prediction on ribozyme assays, supervised, contiguous cross validation25 evaluations · 25 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench CCV-CORR-TRNA: Fitness prediction on tRNA assays, supervised, contiguous cross validation24 evaluations · 24 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench DMS-CCV: Overall fitness prediction on NABench deep mutational scanning assays, Contiguous cross validation Spearman ρ25 evaluations · 25 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench DMS-FS: Overall fitness prediction on NABench deep mutational scanning assays, Few-shot Spearman ρ25 evaluations · 25 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench DMS-RCV: Overall fitness prediction on NABench deep mutational scanning assays, Random cross validation Spearman ρ25 evaluations · 25 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC25 evaluations · 25 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench DMS-ZS-CORR: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot Spearman ρ25 evaluations · 25 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench DMS-ZS-MCC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot MCC25 evaluations · 25 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG25 evaluations · 25 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench FS-CORR-APTAMER: Fitness prediction on aptamer assays, few-shot26 evaluations · 26 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench FS-CORR-ENHANCER: Fitness prediction on enhancer assays, few-shot26 evaluations · 26 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench FS-CORR-MRNA: Fitness prediction on mRNA assays, few-shot26 evaluations · 26 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench FS-CORR-PROMOTER: Fitness prediction on promoter assays, few-shot26 evaluations · 26 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench FS-CORR-RIBOZYME: Fitness prediction on ribozyme assays, few-shot26 evaluations · 26 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench FS-CORR-TRNA: Fitness prediction on tRNA assays, few-shot25 evaluations · 25 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench RCV-CORR-APTAMER: Fitness prediction on aptamer assays, supervised, random cross validation26 evaluations · 26 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench RCV-CORR-ENHANCER: Fitness prediction on enhancer assays, supervised, random cross validation26 evaluations · 26 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench RCV-CORR-MRNA: Fitness prediction on mRNA assays, supervised, random cross validation26 evaluations · 26 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench RCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, random cross validation26 evaluations · 26 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench RCV-CORR-RIBOZYME: Fitness prediction on ribozyme assays, supervised, random cross validation26 evaluations · 26 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench RCV-CORR-TRNA: Fitness prediction on tRNA assays, supervised, random cross validation26 evaluations · 26 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench SELEX-FS: Overall fitness prediction on NABench SELEX assays, Few-shot Spearman ρ26 evaluations · 26 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ25 evaluations · 25 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench SELEX-ZS-AUC: Overall fitness prediction on NABench SELEX assays, Zero-shot AUC26 evaluations · 26 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench SELEX-ZS-CORR: Overall fitness prediction on NABench SELEX assays, Zero-shot Spearman ρ26 evaluations · 26 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench SELEX-ZS-MCC: Overall fitness prediction on NABench SELEX assays, Zero-shot MCC26 evaluations · 26 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench SELEX-ZS-NDCG: Overall fitness prediction on NABench SELEX assays, Zero-shot NDCG26 evaluations · 26 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench ZS-AUC-APTAMER: Fitness prediction on aptamer assays, zero-shot26 evaluations · 26 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench ZS-AUC-ENHANCER: Fitness prediction on enhancer assays, zero-shot26 evaluations · 26 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench ZS-AUC-MRNA: Fitness prediction on mRNA assays, zero-shot26 evaluations · 26 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench ZS-AUC-PROMOTER: Fitness prediction on promoter assays, zero-shot26 evaluations · 26 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench ZS-AUC-RIBOZYME: Fitness prediction on ribozyme assays, zero-shot26 evaluations · 26 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench ZS-AUC-TRNA: Fitness prediction on tRNA assays, zero-shot24 evaluations · 24 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench ZS-CORR-APTAMER: Fitness prediction on aptamer assays, zero-shot27 evaluations · 27 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench ZS-CORR-ENHANCER: Fitness prediction on enhancer assays, zero-shot26 evaluations · 26 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench ZS-CORR-MRNA: Fitness prediction on mRNA assays, zero-shot27 evaluations · 27 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench ZS-CORR-PROMOTER: Fitness prediction on promoter assays, zero-shot27 evaluations · 27 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench ZS-CORR-RIBOZYME: Fitness prediction on ribozyme assays, zero-shot27 evaluations · 27 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NABench ZS-CORR-TRNA: Fitness prediction on tRNA assays, zero-shot25 evaluations · 25 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Natural vs artificial microbial genome sequence3 evaluations · 9 rows3 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
non-coding RNA pairwise interaction prediction1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Interaction-pair splitting does not guarantee unseen RNA identities across partitions.
  • Random baseline AUPRC reflects class prevalence; do not treat it as a fitted model run.
  • CUPID variants are distinct adaptations; no uncertainty printed.
Open Problems label projection CENGEN-BATCH-ACCURACY: Label projection on CeNGEN (split by batch), Accuracy16 evaluations · 16 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Open Problems label projection CENGEN-BATCH-F1-MACRO: Label projection on CeNGEN (split by batch), Macro F1 score16 evaluations · 16 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Open Problems label projection CENGEN-BATCH-F1: Label projection on CeNGEN (split by batch), F1 score16 evaluations · 16 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Open Problems label projection CENGEN-RANDOM-ACCURACY: Label projection on CeNGEN (random split), Accuracy16 evaluations · 16 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Open Problems label projection CENGEN-RANDOM-F1-MACRO: Label projection on CeNGEN (random split), Macro F1 score16 evaluations · 16 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Open Problems label projection CENGEN-RANDOM-F1: Label projection on CeNGEN (random split), F1 score16 evaluations · 16 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Open Problems label projection PANCREAS-BATCH-ACCURACY: Label projection on Pancreas (by batch), Accuracy16 evaluations · 16 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Open Problems label projection PANCREAS-BATCH-F1-MACRO: Label projection on Pancreas (by batch), Macro F1 score16 evaluations · 16 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Open Problems label projection PANCREAS-BATCH-F1: Label projection on Pancreas (by batch), F1 score16 evaluations · 16 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Open Problems label projection PANCREAS-RANDOM-ACCURACY: Label projection on Pancreas (random split), Accuracy16 evaluations · 16 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Open Problems label projection PANCREAS-RANDOM-F1-MACRO: Label projection on Pancreas (random split), Macro F1 score16 evaluations · 16 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Open Problems label projection PANCREAS-RANDOM-F1: Label projection on Pancreas (random split), F1 score16 evaluations · 16 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-ACCURACY: Label projection on Pancreas (random split with label noise), Accuracy16 evaluations · 16 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1-MACRO: Label projection on Pancreas (random split with label noise), Macro F1 score16 evaluations · 16 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score16 evaluations · 16 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Open Problems label projection TABULA-MURIS-SENIS-LUNG-RANDOM-ACCURACY: Label projection on Tabula Muris Senis Lung (random split), Accuracy16 evaluations · 16 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Open Problems label projection TABULA-MURIS-SENIS-LUNG-RANDOM-F1-MACRO: Label projection on Tabula Muris Senis Lung (random split), Macro F1 score16 evaluations · 16 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Open Problems label projection TABULA-MURIS-SENIS-LUNG-RANDOM-F1: Label projection on Tabula Muris Senis Lung (random split), F1 score16 evaluations · 16 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Open Problems label projection ZEBRAFISH-LABS-ACCURACY: Label projection on Zebrafish (by laboratory), Accuracy16 evaluations · 16 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Open Problems label projection ZEBRAFISH-LABS-F1-MACRO: Label projection on Zebrafish (by laboratory), Macro F1 score16 evaluations · 16 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Open Problems label projection ZEBRAFISH-LABS-F1: Label projection on Zebrafish (by laboratory), F1 score16 evaluations · 16 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Open Problems label projection ZEBRAFISH-RANDOM-ACCURACY: Label projection on Zebrafish (random split), Accuracy16 evaluations · 16 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Open Problems label projection ZEBRAFISH-RANDOM-F1-MACRO: Label projection on Zebrafish (random split), Macro F1 score16 evaluations · 16 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Open Problems label projection ZEBRAFISH-RANDOM-F1: Label projection on Zebrafish (random split), F1 score16 evaluations · 16 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
pathogen detection1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Comparison blocked: Section 4.3 lacks exact sample/split manifest and reference-label construction.
  • Section 4.2 five-fold procedure concerns other datasets and cannot be assigned to Table 3.
  • Do not claim the genomic experiment is absent: Section 4.3 explicitly describes it.
Pathological complete response from inferred tumour composition0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
PBMC cell-type classification2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Complete raw table acquired. Celltype accuracy is distinct from cellstate and time/memory. Time formatting and hardware need review before efficiency comparisons; no new timing claim accepted. Structured extraction pending.
Perturbation response0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • A task guide cannot merge perturbation identities, context holdouts, gene subsets or DEG metrics into one leaderboard.
  • Primary figures/source data must be extracted before adding new numerical comparisons.
PerturBench CB-COSINE-RANK: combination prediction on Norman19, Cosine LogFC rank9 evaluations · 9 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PerturBench CB-COSINE: combination prediction on Norman19, Cosine similarity of log fold change9 evaluations · 9 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PerturBench CB-RMSE-RANK: combination prediction on Norman19, RMSE mean rank9 evaluations · 9 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PerturBench CB-RMSE: combination prediction on Norman19, RMSE of the mean9 evaluations · 9 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PerturBench CT-COSINE-RANK: covariate transfer on Srivatsan20, Cosine LogFC rank10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PerturBench CT-COSINE: covariate transfer on Srivatsan20, Cosine similarity of log fold change10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PerturBench CT-RMSE-RANK: covariate transfer on Srivatsan20, RMSE mean rank10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PerturBench CT-RMSE: covariate transfer on Srivatsan20, RMSE of the mean10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PFMBench ANTI-RES: Antibiotic resistance12 evaluations · 12 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PFMBench BINDING-DB: BindingDB12 evaluations · 12 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PFMBench CLONING-CLF: Cloning CLF12 evaluations · 12 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PFMBench DEEPLOC2: DeepLoc2 Multi12 evaluations · 12 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PFMBench DEEPSOL: DeepSol12 evaluations · 12 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PFMBench EC: Enzyme Commission12 evaluations · 12 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PFMBench MAT-PROD: Material production12 evaluations · 12 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PFMBench METAL-ION: Metal ion binding12 evaluations · 12 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PFMBench PDB-BIND: PDBbind12 evaluations · 12 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PFMBench PROTEINGYM-ZS: ProteinGym zero-shot variant effect prediction9 evaluations · 9 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PFMBench SEC-STRUCT: Secondary structure12 evaluations · 12 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PFMBench STABILITY: TAPE_Stability12 evaluations · 12 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Phage / pathogen reads0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • The broad guide has no single common test population. No sequence-design instructions or pathogen enhancement content is needed for detection benchmarking.
  • Full paired numerical figure data remain unextracted; no estimated graph heights.
Physically valid protein–ligand pose selection2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Complete raw table acquired. Source compares selected algorithm versusSBS percohort; gap is derived difference, not new model score. Five-fold means and paired-significance stars do not imply confidence intervals. Structured extraction pending.
polyadenylation site detection1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Raw complete comparison acquired. Few-shot versus fine-tuning and Gene-Gene versus Intergenic-Gene conditions cannot share a chart group; NT100M and 500M are different configurations. Structured extraction pending.
Prediction of VHH expression from sequence0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Protein design / inverse folding0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • Protein design is a broad task. ProteinMPNN reports native sequence recovery on 402 backbones and separate noisy-backbone/experimental design evaluations; no general protein-design ranking. New primary paper pinned, concrete protocol extraction required.
protein function annotation1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
protein localization classification1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Table 2 architectures and pretraining datasets differ; HPA-FoV and HPA-SC are separate protocols.
  • Do not attach Cell Painting MoA AUPRC to protein localization.
  • Table 6 ensembling is five MLPs with threshold/prediction averaging; not the base frozen model alone.
protein variant fitness prediction1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Pinned source PDF retained; source-specific assay aggregation and substitution/indel scope require full table mapping. Existing result preserved; structured extraction pending.
protein variant-effect classification1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Artifact returned HTML rather than XML, so XML table parser intentionally rejected it. Prior reviewed observation retained. Complete table extraction and source-version comparison remain pending.
protein-ligand binding affinity prediction1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
protein-protein binding-site prediction1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
protein-protein interaction prediction7 evaluations · 34 rows11 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
protein-protein interaction prediction1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Complete raw tables acquired. Tables 3/4 matched four-method experiments;Table 5 combines different datasets and cannot form a common ranking. Units mix percentaccuracy and fractionalmetrics. Structured extraction pending.
protein-small molecule binding-site prediction12 evaluations · 45 rows12 source-scoped figuresChecked result tables available.
Scope and remaining work
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
Protein–ligand binding affinity prediction2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Complete raw tables acquired. Table 1PCC footnote sayspercentcorrectclassification whileTable 2 labelsPearson; ambiguity quarantined. Literature comparison rows have different training histories. Structured extraction pending.
Protein–ligand binding affinity scoring37 evaluations · 82 rows9 source-scoped figuresChecked result tables available.
Scope and remaining work
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
Protein–ligand binding energy prediction2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • RMSE is lower-is-better; do not mix correlation and energy errors.
  • Conventional-function rows must retain software suffixes and scoring settings; exact common test/context needs methods review before merging Tables 1–2 into one chart.
Protein–ligand pose0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • complete comparable numeric result batch: Specific candidate tables and protocol boundaries are documented; no graph values or incomplete winner-only selection are converted into publishable rows.
Protein–ligand pose prediction2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
Protein–ligand pose prediction1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Pose benchmark values are mainly in figures; Table 1 reports ablation/cycling conditions and cannot substitute for complete competitor pose matrix. Source artifacts acquired; no scores estimated from pixels.
Protein–ligand virtual screening2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Target-level EF, mean EF and counts above EF cutoffs are separate metrics.
  • Do not describe pKd-score or pKd-screen as experimentally calibrated affinity from the EF metric.
  • All table scores are conditional on the stated docked poses.
ProteinBench AB-ACCURACY-AAR: Accuracy AAR8 evaluations · 8 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench AB-ACCURACY-RMSD: Accuracy RMSD8 evaluations · 8 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench AB-ACCURACY-TM-SCORE: Accuracy TM-score8 evaluations · 8 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench AB-FUNCTIONALITY-BINDING-ENERGY: Functionality Binding Energy8 evaluations · 8 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench AB-RATIONALITY-CLASHES-INNER: Rationality Clashes-inner8 evaluations · 8 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench AB-RATIONALITY-CLASHES-OUTER: Rationality Clashes-outer8 evaluations · 8 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench AB-RATIONALITY-CN-SCORE: Rationality CN-score8 evaluations · 8 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench AB-RATIONALITY-SCRMSD: Rationality scRMSD8 evaluations · 8 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench AB-RATIONALITY-SEQNAT: Rationality SeqNat8 evaluations · 8 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench AB-RATIONALITY-TOTAL-ENERGY: Rationality Total Energy8 evaluations · 8 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench AB-SPECIFICITY-PHR: Specificity PHR8 evaluations · 8 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench AB-SPECIFICITY-SEQSIM-INNER: Specificity SeqSim-inner4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench AB-SPECIFICITY-SEQSIM-OUTER: Specificity SeqSim-outer8 evaluations · 8 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench BB-LENGTH-100-DIVERSITY-MAX-CLUST: length 100, Diversity Max Clust.9 evaluations · 9 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench BB-LENGTH-100-DIVERSITY-PAIRWISE-TM: length 100, Diversity pairwise TM9 evaluations · 9 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench BB-LENGTH-100-NOVELTY-MAX-TM: length 100, Novelty Max TM8 evaluations · 8 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench BB-LENGTH-100-QUALITY-SCRMSD: length 100, Quality scRMSD9 evaluations · 9 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench BB-LENGTH-100-QUALITY-SCTM: length 100, Quality scTM9 evaluations · 9 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench BB-LENGTH-300-DIVERSITY-MAX-CLUST: length 300, Diversity Max Clust.9 evaluations · 9 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench BB-LENGTH-300-DIVERSITY-PAIRWISE-TM: length 300, Diversity pairwise TM9 evaluations · 9 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench BB-LENGTH-300-NOVELTY-MAX-TM: length 300, Novelty Max TM8 evaluations · 8 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench BB-LENGTH-300-QUALITY-SCRMSD: length 300, Quality scRMSD9 evaluations · 9 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench BB-LENGTH-300-QUALITY-SCTM: length 300, Quality scTM9 evaluations · 9 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench BB-LENGTH-50-DIVERSITY-MAX-CLUST: length 50, Diversity Max Clust.9 evaluations · 9 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench BB-LENGTH-50-DIVERSITY-PAIRWISE-TM: length 50, Diversity pairwise TM9 evaluations · 9 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench BB-LENGTH-50-NOVELTY-MAX-TM: length 50, Novelty Max TM8 evaluations · 8 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench BB-LENGTH-50-QUALITY-SCRMSD: length 50, Quality scRMSD9 evaluations · 9 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench BB-LENGTH-50-QUALITY-SCTM: length 50, Quality scTM9 evaluations · 9 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench BB-LENGTH-500-DIVERSITY-MAX-CLUST: length 500, Diversity Max Clust.9 evaluations · 9 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench BB-LENGTH-500-DIVERSITY-PAIRWISE-TM: length 500, Diversity pairwise TM9 evaluations · 9 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench BB-LENGTH-500-NOVELTY-MAX-TM: length 500, Novelty Max TM8 evaluations · 8 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench BB-LENGTH-500-QUALITY-SCRMSD: length 500, Quality scRMSD9 evaluations · 9 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench BB-LENGTH-500-QUALITY-SCTM: length 500, Quality scTM9 evaluations · 9 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench CO-LENGTH-100-DIVERSITY-MAX-CLUST: length 100, Diversity Max Clust.5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench CO-LENGTH-100-NOVELTY-MAX-TM: length 100, Novelty Max TM4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench CO-LENGTH-100-QUALITY-SCRMSD: length 100, Quality scRMSD5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench CO-LENGTH-100-QUALITY-SCTM: length 100, Quality scTM5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench CO-LENGTH-200-DIVERSITY-MAX-CLUST: length 200, Diversity Max Clust.5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench CO-LENGTH-200-NOVELTY-MAX-TM: length 200, Novelty Max TM4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench CO-LENGTH-200-QUALITY-SCRMSD: length 200, Quality scRMSD5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench CO-LENGTH-200-QUALITY-SCTM: length 200, Quality scTM5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench CO-LENGTH-300-DIVERSITY-MAX-CLUST: length 300, Diversity Max Clust.5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench CO-LENGTH-300-NOVELTY-MAX-TM: length 300, Novelty Max TM4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench CO-LENGTH-300-QUALITY-SCRMSD: length 300, Quality scRMSD5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench CO-LENGTH-300-QUALITY-SCTM: length 300, Quality scTM5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench CO-LENGTH-500-DIVERSITY-MAX-CLUST: length 500, Diversity Max Clust.5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench CO-LENGTH-500-NOVELTY-MAX-TM: length 500, Novelty Max TM4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench CO-LENGTH-500-QUALITY-SCRMSD: length 500, Quality scRMSD5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench CO-LENGTH-500-QUALITY-SCTM: length 500, Quality scTM5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench FOLD-ACCURACY-GDT-TS-MEAN: Accuracy GDT-TS (mean)5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench FOLD-ACCURACY-GDT-TS-MEDIAN: Accuracy GDT-TS (median)5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench FOLD-ACCURACY-LDDT-MEAN: Accuracy lDDT (mean)5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench FOLD-ACCURACY-LDDT-MEDIAN: Accuracy lDDT (median)5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench FOLD-ACCURACY-RMSD-MEAN: Accuracy RMSD (mean)5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench FOLD-ACCURACY-RMSD-MEDIAN: Accuracy RMSD (median)5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench FOLD-ACCURACY-TM-SCORE-MEAN: Accuracy TM-score (mean)5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench FOLD-ACCURACY-TM-SCORE-MEDIAN: Accuracy TM-score (median)5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench FOLD-QUALITY-CA-BREAK-MEAN: Quality CA break (%) (mean)5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench FOLD-QUALITY-CA-BREAK-MEDIAN: Quality CA break (%) (median)5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench FOLD-QUALITY-CA-CLASH-MEAN: Quality CA clash (%) (mean)5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench FOLD-QUALITY-CA-CLASH-MEDIAN: Quality CA clash (%) (median)5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench FOLD-QUALITY-PEPBOND-BREAK-MEAN: Quality PepBond break (%) (mean)4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench FOLD-QUALITY-PEPBOND-BREAK-MEDIAN: Quality PepBond break (%) (median)4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-100-PLDDT: De novo backbones based sequence design, length 100 pLDDT4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-100-SCTM: De novo backbones based sequence design, length 100 scTM4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-200-PLDDT: De novo backbones based sequence design, length 200 pLDDT4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-200-SCTM: De novo backbones based sequence design, length 200 scTM4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-300-PLDDT: De novo backbones based sequence design, length 300 pLDDT4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-300-SCTM: De novo backbones based sequence design, length 300 scTM4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-400-PLDDT: De novo backbones based sequence design, length 400 pLDDT4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-400-SCTM: De novo backbones based sequence design, length 400 scTM4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-500-PLDDT: De novo backbones based sequence design, length 500 pLDDT4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-500-SCTM: De novo backbones based sequence design, length 500 scTM4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench IF-FITTING-EVOLUTION-DISTRIBUTION-CAMEO-AAR: Fitting Evolution Distribution, CAMEO AAR2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench IF-FITTING-EVOLUTION-DISTRIBUTION-CASP-AAR: Fitting Evolution Distribution, CASP AAR2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench SEQ-LENGTH-100-DIVERSITY-MAX-CLUST: length 100, Diversity Max Clust.5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench SEQ-LENGTH-100-DIVERSITY-PAIRWISE-TM: length 100, Diversity pairwise TM5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench SEQ-LENGTH-100-NOVELTY-MAX-TM: length 100, Novelty Max TM4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench SEQ-LENGTH-100-QUALITY-PLDDT: length 100, Quality pLDDT5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench SEQ-LENGTH-100-QUALITY-PPL: length 100, Quality ppl4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench SEQ-LENGTH-200-DIVERSITY-MAX-CLUST: length 200, Diversity Max Clust.5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench SEQ-LENGTH-200-DIVERSITY-PAIRWISE-TM: length 200, Diversity pairwise TM5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench SEQ-LENGTH-200-NOVELTY-MAX-TM: length 200, Novelty Max TM4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench SEQ-LENGTH-200-QUALITY-PLDDT: length 200, Quality pLDDT5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench SEQ-LENGTH-200-QUALITY-PPL: length 200, Quality ppl4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench SEQ-LENGTH-300-DIVERSITY-MAX-CLUST: length 300, Diversity Max Clust.5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench SEQ-LENGTH-300-DIVERSITY-PAIRWISE-TM: length 300, Diversity pairwise TM5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench SEQ-LENGTH-300-NOVELTY-MAX-TM: length 300, Novelty Max TM4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench SEQ-LENGTH-300-QUALITY-PLDDT: length 300, Quality pLDDT5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench SEQ-LENGTH-300-QUALITY-PPL: length 300, Quality ppl4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench SEQ-LENGTH-500-DIVERSITY-MAX-CLUST: length 500, Diversity Max Clust.5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench SEQ-LENGTH-500-DIVERSITY-PAIRWISE-TM: length 500, Diversity pairwise TM5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench SEQ-LENGTH-500-NOVELTY-MAX-TM: length 500, Novelty Max TM4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench SEQ-LENGTH-500-QUALITY-PLDDT: length 500, Quality pLDDT5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinBench SEQ-LENGTH-500-QUALITY-PPL: length 500, Quality ppl4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym mutation effects0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • complete comparable numeric result batch: Specific candidate tables and protocol boundaries are documented; no graph values or incomplete winner-only selection are converted into publishable rows.
ProteinGym SUP-SUB-MSE-AVG: Supervised substitutions, average over splits, MSE10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym SUP-SUB-MSE-CONTIG: Supervised substitutions, contiguous split, MSE10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym SUP-SUB-MSE-MOD: Supervised substitutions, modulo split, MSE10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym SUP-SUB-MSE-RAND: Supervised substitutions, random split, MSE10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym SUP-SUB-SPEARMAN-AVG: Supervised substitutions, average over splits, Spearman10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym SUP-SUB-SPEARMAN-CONTIG: Supervised substitutions, contiguous split, Spearman10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym SUP-SUB-SPEARMAN-MOD: Supervised substitutions, modulo split, Spearman10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym SUP-SUB-SPEARMAN-RAND: Supervised substitutions, random split, Spearman10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym ZS-INDEL-AUC: Zero-shot indels, all assays, AUC9 evaluations · 9 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym ZS-INDEL-SPEARMAN-ALL: Zero-shot indels, all assays, Spearman9 evaluations · 9 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym ZS-INDEL-SPEARMAN-DESIGNED: Zero-shot indels, designed or natural assays, Spearman9 evaluations · 9 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym ZS-INDEL-SPEARMAN-LIBRARY: Zero-shot indels, library assays, Spearman9 evaluations · 9 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym ZS-SUB-AUC: Zero-shot substitutions, AUC21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym ZS-SUB-MCC: Zero-shot substitutions, MCC21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym ZS-SUB-NDCG: Zero-shot substitutions, NDCG@10%21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym ZS-SUB-RECALL: Zero-shot substitutions, top 10% recall21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym ZS-SUB-SPEARMAN: Zero-shot substitutions, Spearman21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
regulatory element identification1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
regulatory sequence classification1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Models differ in architecture, size and pretraining as well as tokenizer, so Table 2 alone does not isolate tokenizer causality.
  • Table 3 offers paired tokenizer comparisons; do not relabel whole-family comparisons as controlled tokenizer ablations.
  • No per-cell uncertainty in Table 2.
regulatory-variant scoring1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • These are trained hybrid models, not zero-shot ARSENAL scores.
  • Keep QTL cohorts and Pearson/Spearman/AUROC separate; verify printed ± definition before plotting error bars.
RNA compound-binding site prediction1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Baselines in Table 4 are taken from Gao et al., Zhu et al. and Chen et al.; this is a literature comparison, not uniformly rerun methods.
  • Do not assign the selected CoBRA pipeline score to RiNALMo alone; absent values are unavailable, not zero.
RNA secondary structure40 evaluations · 160 rows16 source-scoped figuresChecked result tables available.
RNA secondary structure2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Full raw tables acquired. Different family-held-out cohorts and median-over-three versus median-over-two aggregates must stay distinct. Repeated DEBFold row in Table 2 is not new independent evidence; comRNA missing predictions retained. Structured extraction pending.
RNA secondary structure2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Complete raw comparison acquired,11 methods across overall and two length bands; means/SD preserved. F1/INF and precision/recall separate columns; no aggregate across different length cohorts. Structured extraction pending.
RNA secondary structure40 evaluations · 160 rows16 source-scoped figuresChecked result tables available.
Scope and remaining work
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
RNA secondary-structure prediction1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
RNA sequence design1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
RNA splice-site mapping0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • complete comparable numeric result batch: Specific candidate tables and protocol boundaries are documented; no graph values or incomplete winner-only selection are converted into publishable rows.
RNA tertiary structure0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • complete comparable numeric result batch: Specific candidate tables and protocol boundaries are documented; no graph values or incomplete winner-only selection are converted into publishable rows.
RNA-small-molecule binding-site prediction1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Most baseline values are copied from original publications; RNABind is a web-server run.
  • T18/T3/T10 are separate protocols and cannot be pooled as one model score.
  • Unavailable RNet AUC is a dash, not zero.
Runtime of a binder design run0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Simulated metagenome virus-taxon retrieval2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
Simulated prophage-contig detection2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Performance averages over simulation conditions, not independent training seeds; do not use rank as a probability.
  • Benchmark simulation conditions differ from real metagenomic samples.
Small-molecule affinity0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • Binding probability, mixed-measure affinity regression and virtual-screening enrichment are different outcomes.
  • Affinity head mixes biochemical quantities; values are not automatically assay-calibrated Kd.
  • No paper-wide universal affinity score or common ligand denominator.
Strain-level abundance quantification2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Complete raw table acquired. Identified-strain counts/ratios and L1/L2 abundance errors must remain different metrics; MetaPhlAn detection bounds are not exact counts. Structured extraction pending.
Survival prognosis from pretreatment bulk RNA-seq0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
TAPE Contact Prediction10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
TAPE Fluorescence10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
TAPE Remote Homology Detection10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
TAPE Secondary Structure10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
TAPE Stability10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
TDC ADMET benchmark group TDC-AMES: Toxicity: TDC.AMES3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TDC ADMET benchmark group TDC-AQSOL: Absorption: TDC.AqSol3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TDC ADMET benchmark group TDC-BBB: Distribution: TDC.BBB3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TDC ADMET benchmark group TDC-BIOAV: Absorption: TDC.Bioav3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TDC ADMET benchmark group TDC-CACO2: Absorption: TDC.Caco23 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TDC ADMET benchmark group TDC-CL-HEPA: Excretion: TDC.CL-Hepa3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TDC ADMET benchmark group TDC-CL-MICRO: Excretion: TDC.CL-Micro3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TDC ADMET benchmark group TDC-CYP2C9-INHIBITION: Metabolism: TDC.CYP2C9 Inhibition3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TDC ADMET benchmark group TDC-CYP2C9-SUBSTRATE: Metabolism: TDC.CYP2C9 Substrate3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TDC ADMET benchmark group TDC-CYP2D6-INHIBITION: Metabolism: TDC.CYP2D6 Inhibition3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TDC ADMET benchmark group TDC-CYP2D6-SUBSTRATE: Metabolism: TDC.CYP2D6 Substrate3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TDC ADMET benchmark group TDC-CYP3A4-INHIBITION: Metabolism: TDC.CYP3A4 Inhibition3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TDC ADMET benchmark group TDC-CYP3A4-SUBSTRATE: Metabolism: TDC.CYP3A4 Substrate3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TDC ADMET benchmark group TDC-DILI: Toxicity: TDC.DILI3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TDC ADMET benchmark group TDC-HALF-LIFE: Excretion: TDC.Half Life3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TDC ADMET benchmark group TDC-HERG: Toxicity: TDC.hERG3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TDC ADMET benchmark group TDC-HIA: Absorption: TDC.HIA3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TDC ADMET benchmark group TDC-LD50: Toxicity: TDC.LD503 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TDC ADMET benchmark group TDC-LIPO: Absorption: TDC.Lipo3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TDC ADMET benchmark group TDC-PGP: Absorption: TDC.Pgp3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TDC ADMET benchmark group TDC-PPBR: Distribution: TDC.PPBR3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TDC ADMET benchmark group TDC-VD: Distribution: TDC.VDss3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
transcription-factor DNA binding-site prediction6 evaluations · 12 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
Translation / RNA stability0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • Translation and stability encompass separate species, cell contexts, transcript regions and assays. Fresh primary XML pinned; concrete mRNABench protocols should be linked instead of attaching all suite results to broad task.
translation-efficiency prediction1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
Treatment benefit (predictive biomarker) from bulk RNA-seq0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
unseen-species genus classification1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Table does not give uncertainty for each genus accuracy; BLAST is an alignment reference, not a pretrained encoder.
vaccine-antigen candidate prediction4 evaluations · 22 rows7 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
viral sequence detection1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
Zero-shot fitness prediction on RNAGym ncRNA DMS assays0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Zero-shot substitution mutation effects: stability2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Other functional-category columns do not belong to the stability benchmark.
  • This pinned 2023 paper table is not the latest ProteinGym leaderboard; do not overwrite later-version results.
  • MSA and structure inputs differ across model categories; no universal sequence-only ranking.
Zero-shot variant effect prediction2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Table contains two zero-shot mean absolute Spearman values already in catalogue; no new independent observations warranted. Other Table 2 tasks are different benchmarks. Full raw table and source receipt retained.

Protocols

1567 pages · 1536 with results · 326 with charts.

PageEvaluations and metric rowsChartsCollection status
AAV low-vs-high (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
AAV two-vs-many (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ABCA4 deep-intronic variants: classification against mini- or midigene splicing results (Riepe et al. Table 4)9 evaluations · 99 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ABCA4 noncanonical splice-site variants: classification against mini- or midigene splicing results (Riepe et al. Table 3)11 evaluations · 121 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Abdelaal et al. 2019 inter-dataset brain comparison: VISp/ALM/MTG, 34-population annotation (Figure S10 Panel B)9 evaluations · 9 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Abdelaal et al. 2019 intra-dataset 5-fold CV: Baron Human pancreatic dataset4 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Acetyltransferase dataset stability ranking, Spearman correlation (Chu et al. 2024 Table 1)7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3)5 evaluations · 35 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Acute leukaemia whole RNA-seq fusion detection against conventional diagnostics (Kim et al. 2026)1 evaluation · 83 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Adamson et al. 2016 Perturb-seq, K562 CRISPRi single perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2)15 evaluations · 88 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Adamson: expression prediction for unseen single perturbations (Ahlmann-Eltze et al. 2025 Fig. 2a and Extended Data Fig. 8a)7 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Adaptyv EGFR competition BLI affinity3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Adaptyv EGFR competition BLI binding screen4 evaluations · 9 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Adaptyv EGFR competition cell-free expression rate5 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
African-ancestry LCL caQTL classification (AlphaGenome paper)3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
African-ancestry LCL caQTL effect-size prediction (AlphaGenome paper)3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
All fusions, conventional RNA-seq of haematologic cell lines, consensus truth (Tamura et al. 2026 Supplementary Table 3)12 evaluations · 72 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
All fusions, targeted RNA-seq of haematologic cell lines, consensus truth (Tamura et al. 2026 Supplementary Table 3)12 evaluations · 72 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Allelic reporter effect correlation in HeLa (Manzo et al. 2025 Table 1)24 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Allelic reporter effect correlation in HepG2 (Manzo et al. 2025 Table 1)24 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Allelic reporter effect correlation in K562 (Manzo et al. 2025 Table 1)24 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Allelic reporter effect correlation in NPC (Manzo et al. 2025 Table 1)24 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
AlphaBind PEM held-out antigen, pairwise accuracy4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
AlphaBind PP489 held-out antigen, pairwise accuracy4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
AlphaBind TRA held-out antigen, pairwise accuracy4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
AlphaBind VHH72 held-out antigen, pairwise accuracy4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
AlphaProteo best per-target binder affinity by HTRF25 evaluations · 25 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
AlphaProteo expression and HTRF confirmation funnel for yeast-display hits28 evaluations · 28 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
AlphaProteo yeast-display binding screen, hit at binding signal above 0.226 evaluations · 26 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
AlphaProteo yeast-display binding screen, hit at binding signal above 1.3 (IL-17A)2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Alternative polyadenylation coverage ratios (AlphaGenome paper)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • Reported scores remain quarantined because the supplementary table and another source disagree; see the protocol limitations for the exact discrepancy.
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
AML tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)15 evaluations · 60 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Amylase by mutation count (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Amylase one-to-many (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Annotation of a held-out batch after fine-tuning (HyCell report)4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Annotation transfer with 15-nearest neighbours (HyCell report)16 evaluations · 16 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Annotation transfer with logistic regression (HyCell report)16 evaluations · 16 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Apparent dissociation constant of a selected minibinder design by biolayer interferometry4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Apparent dissociation constant of a selected VHH design by biolayer interferometry4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Arch retrieval (DGEB) (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ArchiveII (RNA secondary structure)10 evaluations · 40 rows4 source-scoped figuresChecked result tables available.
Scope and remaining work
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
AssayBench-Loop adaptive hit discovery: 10 rounds of 100 genes on 20 held-out CRISPR screens53 evaluations · 530 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
AssayBench: rank 100 candidate genes for a described CRISPR screen48 evaluations · 144 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ATAC prediction on held-out peaks (AlphaGenome paper)2 evaluations · 6 rows3 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
ATAC track prediction at 128 bp (AlphaGenome paper)3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
ATAC track prediction at 32 bp (AlphaGenome paper)2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
Author MFASS splice-disruption prediction (AlphaGenome paper)2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
AVI feature ablation, ClinVar column, AUPRC (AlphaGenome Atlas Table S2)14 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
AVI feature ablation, ncVar column, AUPRC (AlphaGenome Atlas Table S2)14 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
AVI feature ablation, SGE column, AUPRC (AlphaGenome Atlas Table S2)14 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
AVI feature ablation, TraitGym Complex column, AUPRC (AlphaGenome Atlas Table S2)14 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
AVI feature ablation, TraitGym Mendelian column, AUPRC (AlphaGenome Atlas Table S2)14 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
B-cell to plasma-cell pseudotime ordering, all cells (HyCell report)4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
B-cell to plasma-cell pseudotime ordering, donor mean (HyCell report)4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BacBench antibiotic resistance, binary linear probe AUPRC12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BacBench antibiotic resistance, binary linear probe AUROC12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BacBench antibiotic resistance, MIC regression Pearson correlation12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BacBench antibiotic resistance, MIC regression R squared12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BacBench essential gene prediction, linear probe AUPRC12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BacBench essential gene prediction, linear probe AUROC12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BacBench operon identification, zero-shot AUPRC12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BacBench operon identification, zero-shot AUROC12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BacBench phenotypic trait prediction, linear probe AUPRC12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BacBench phenotypic trait prediction, linear probe AUROC12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BacBench protein-protein interaction, linear probe AUPRC12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BacBench protein-protein interaction, linear probe AUROC12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BacBench protein-protein interaction, zero-shot AUPRC12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BacBench protein-protein interaction, zero-shot AUROC12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BacBench strain clustering, adjusted Rand index6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BacBench strain clustering, average silhouette width6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BacBench strain clustering, normalised mutual information6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Base-resolution RNA-seq prediction (AlphaGenome paper)2 evaluations · 4 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
BEELINE 2020 Figure 2 · BF12 evaluations · 24 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 2 · BFC12 evaluations · 24 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 2 · CY12 evaluations · 24 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 2 · LI12 evaluations · 24 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 2 · LL12 evaluations · 24 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 2 · TF12 evaluations · 24 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 4 · GSD12 evaluations · 48 rows4 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 4 · HSC12 evaluations · 48 rows4 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 4 · mCAD12 evaluations · 48 rows4 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 4 · VSC12 evaluations · 36 rows3 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · hESC · Cell-type specific ChIP-Seq network, TFs+1000 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · hESC · Cell-type specific ChIP-Seq network, TFs+500 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · hESC · Non-specific ChIP-Seq network, TFs+1000 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · hESC · Non-specific ChIP-Seq network, TFs+500 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · hESC · STRING network, TFs+1000 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · hESC · STRING network, TFs+500 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · hHep · Cell-type specific ChIP-Seq network, TFs+1000 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · hHep · Cell-type specific ChIP-Seq network, TFs+500 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · hHep · Non-specific ChIP-Seq network, TFs+1000 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · hHep · Non-specific ChIP-Seq network, TFs+500 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · hHep · STRING network, TFs+1000 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · hHep · STRING network, TFs+500 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · mDC · Cell-type specific ChIP-Seq network, TFs+1000 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · mDC · Cell-type specific ChIP-Seq network, TFs+500 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · mDC · Non-specific ChIP-Seq network, TFs+1000 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · mDC · Non-specific ChIP-Seq network, TFs+500 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · mDC · STRING network, TFs+1000 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · mDC · STRING network, TFs+500 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · mESC · Cell-type specific ChIP-Seq network, TFs+1000 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · mESC · Cell-type specific ChIP-Seq network, TFs+500 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · mESC · log/gof network, TFs+1000 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · mESC · log/gof network, TFs+500 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · mESC · Non-specific ChIP-Seq network, TFs+1000 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · mESC · Non-specific ChIP-Seq network, TFs+500 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · mESC · STRING network, TFs+1000 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · mESC · STRING network, TFs+500 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · mHSC-E · Cell-type specific ChIP-Seq network, TFs+1000 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · mHSC-E · Cell-type specific ChIP-Seq network, TFs+500 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · mHSC-E · Non-specific ChIP-Seq network, TFs+1000 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · mHSC-E · Non-specific ChIP-Seq network, TFs+500 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · mHSC-E · STRING network, TFs+1000 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · mHSC-E · STRING network, TFs+500 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · MHSC-GM · Cell-type specific ChIP-Seq network, TFs+1000 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · MHSC-GM · Cell-type specific ChIP-Seq network, TFs+500 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · MHSC-GM · Non-specific ChIP-Seq network, TFs+1000 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · MHSC-GM · Non-specific ChIP-Seq network, TFs+500 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · MHSC-GM · STRING network, TFs+1000 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · MHSC-GM · STRING network, TFs+500 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · mHSC-L · Cell-type specific ChIP-Seq network, TFs+1000 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · mHSC-L · Cell-type specific ChIP-Seq network, TFs+500 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · mHSC-L · Non-specific ChIP-Seq network, TFs+1000 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · mHSC-L · Non-specific ChIP-Seq network, TFs+500 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · mHSC-L · STRING network, TFs+1000 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BEELINE 2020 Figure 5 · mHSC-L · STRING network, TFs+500 genes6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BenchBench-Cloning aggregate score over all 65 tasks0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BenchBench-Cloning construct design, per task: attempts passed out of 5, deterministic grading only0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BenchBench-Cloning construct design, per task: attempts passed out of 5, deterministic grading with a rubric model judge0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BenchBench-Cloning construct design: single-attempt pass rate over 15 tasks0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BenchBench-Cloning protocol development: pass@10 over 50 tasks0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BenchBench-Cloning protocol development: pass@5 over 50 tasks0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BenchBench-Cloning protocol development: single-attempt pass rate over 50 tasks0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BenchBench-Cloning protocol development: tasks solved at least once in the ten recorded attempts, out of 500 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BenchBench-Cloning protocol development: tasks solved in every one of the ten recorded attempts, out of 500 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Benet-Pages BRCA1/BRCA2 VUS reclassification: ACMG/AMP + SVI step (t2)1 evaluation · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Benet-Pages BRCA1/BRCA2 VUS reclassification: ENIGMA VCEP step (t3)1 evaluation · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Bennett VHH computational success rate under an AlphaFold3 filter6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Bennett VHH computational success rate under the fine-tuned RoseTTAFold2 filter18 evaluations · 18 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Bennett VHH design, E. coli expression and single-concentration SPR screen of 96 designs3 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Bennett VHH design, yeast surface display screen of 9,000 designs with SPR confirmation3 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BERTax Closely related dataset: taxonomic classification at superkingdom and phylum (Mock et al. 2022)9 evaluations · 54 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BERTax Distantly related dataset: taxonomic classification at superkingdom and phylum (Mock et al. 2022)9 evaluations · 72 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BERTax Final model dataset: taxonomic classification at superkingdom and phylum, and genus (Mock et al. 2022)9 evaluations · 27 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Best DockQ against sampling depth on cognate nanobody-antigen complexes4 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BF16 path minus reference sampler in scTM at fixed diversity (HyInv report)4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Bgl3 dataset stability ranking, Spearman correlation (Chu et al. 2024 Table 1)7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BglB dataset stability ranking, Spearman correlation (Chu et al. 2024 Table 1)7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BindCraft best per-target binder affinity12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BindCraft experimental success rate averaged over its 12 benchmark targets1 evaluation · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BindCraft per-target binding screen, hit where a binding signal was observed10 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BioDiscoveryAgent 1-gene perturbation design: hit ratio after 5 rounds of 128 genes120 evaluations · 240 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BioML-bench drug discovery domain: agent leaderboard percentile over 9 tasks10 evaluations · 34 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BioML-bench protein engineering domain: agent leaderboard percentile over 6 tasks10 evaluations · 34 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BioML-bench single cell omics domain: agent leaderboard percentile over 5 tasks10 evaluations · 44 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Blood single-cell to isoform, direction accuracy for COVID-19 against healthy draws, top 5% of genes2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Blood single-cell to isoform, direction accuracy for day 0 to day 14 change, top 5% of genes2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
bpRNA-TS0 (RNA secondary structure)10 evaluations · 40 rows4 source-scoped figuresChecked result tables available.
Scope and remaining work
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
BRCA1 BayesDel evidence calibration1 evaluation · 15 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BRCA1 functional truth set, binary in silico calls (Cubuk et al. 2021)84 evaluations · 247 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BRCA1 generic BayesDel threshold evidence-code assignment1 evaluation · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BRCA1 MAVE LoF discrimination at the PP3 threshold (Ramadane-Morchadi et al. 2025 Table 2)6 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BRCA1 MAVE PP3/BP4 evidence strength by score threshold (Ramadane-Morchadi et al. 2025 Table 1)8 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BRCA1 saturation genome editing, synonymous and intronic SNVs: transcriptome-normalised sensitivity at a 10% background call rate (Smith and Kitzman Table S2)8 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BRCA2 BayesDel evidence calibration1 evaluation · 15 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BRCA2 functional truth set, binary in silico calls (Cubuk et al. 2021)84 evaluations · 226 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
BRCA2 generic BayesDel threshold evidence-code assignment1 evaluation · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Breast cancer pCR, ER+/HER2- external cohorts, AUC of a model fitted on TransNEO6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Breast cancer pCR, HER2+ external cohorts, AUC of a model fitted on TransNEO4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CA-lDDT of designed sequences under ESMFold2 (HyInv report)60 evaluations · 60 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CACHE #3 merged Round 1 library prediction per workflow (Herasymenko et al. 2026 Table S8)19 evaluations · 171 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CACHE #3 Round 1 own-selection outcome per workflow (Herasymenko et al. 2026 Table S8)23 evaluations · 161 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CAFA3 BPO all organisms; type1 no-knowledge; mode1 · CAFA3 final benchmark; BPO; all; type1; mode1146 evaluations · 146 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CAFA3 CCO all organisms; type1 no-knowledge; mode1 · CAFA3 final benchmark; CCO; all; type1; mode1146 evaluations · 146 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CAFA3 MFO all organisms; type1 no-knowledge; mode1 · CAFA3 final benchmark; MFO; all; type1; mode1146 evaluations · 146 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CAGE track prediction at 128 bp (AlphaGenome paper)3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
CAGE track prediction at 32 bp (AlphaGenome paper)2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
CAGI5 saturation MPRA variant effect correlation, HepG2 (Tang et al. 2025 Table 1)14 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CAGI5 saturation MPRA variant effect correlation, K562 (Tang et al. 2025 Table 1)14 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CAMI II marine genome binning; pooled short-read gold-standard assembly; circular elements excluded · marmgCAMI2_short_read_pooled_gold_standard_assembly16 evaluations · 256 rows16 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CAPRI round 61 predictor; submitted model 1; T312.1 · CAPRI round 61 T312.125 evaluations · 100 rows4 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CAPRI round 61 predictor; submitted model 1; T314.1 · CAPRI round 61 T314.125 evaluations · 100 rows4 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CAPRI round 61 predictor; submitted model 1; T315.1 · CAPRI round 61 T315.125 evaluations · 100 rows4 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CAPRI round 61 predictor; submitted model 1; T316.1 · CAPRI round 61 T316.125 evaluations · 100 rows4 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Carrier plasma protein levels for rare splice-region variants, UK Biobank (SpliceAI2 paper, Pearson)4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CASF-2016 docking (Protein–ligand binding affinity scoring)9 evaluations · 27 rows3 source-scoped figuresChecked result tables available.
Scope and remaining work
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
CASF-2016 ranking (Protein–ligand binding affinity scoring)9 evaluations · 27 rows3 source-scoped figuresChecked result tables available.
Scope and remaining work
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
CASF-2016 scoring (Protein–ligand binding affinity scoring)9 evaluations · 9 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
CASP16 affinity challenge, Boltz-2 against the top-ranked participants10 evaluations · 90 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CASP16 protein domain; first submitted model; T1201-D1 · CASP16 T1201-D190 evaluations · 270 rows6 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Causal-gene rank in 152 KGD trio-family exomes across parameter protocols (Yuan et al. 2024 Table 1)13 evaluations · 91 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Causal-gene rank in 209 in-house exomes, default singleton runs (Yuan et al. 2022 SM Table 3)11 evaluations · 77 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Causal-gene rank in 305 DDD exomes, default singleton runs (Yuan et al. 2022 SM Table 3)11 evaluations · 77 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Causal-gene rank in 305 DDD trio-family exomes across parameter protocols (Yuan et al. 2024 Table 1)13 evaluations · 91 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CCGA substudy 1 training set: cancer signal sensitivity at 98% specificity under 10-fold cross-validation9 evaluations · 9 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CCGA substudy 1 validation set: cancer signal origin accuracy among jointly detected cancers3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CCGA substudy 1 validation set: cancer signal sensitivity at 98% specificity10 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CD4 T-cell split against sequencing chemistry, NMI (HyCell report)1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ceiling-normalised comparison, EditJumps, two families, 200 references: Covariance (% of ceiling)1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ceiling-normalised comparison, EditJumps, two families, 200 references: MIP (% of ceiling)1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ceiling-normalised comparison, EditJumps, two families, 200 references: Pairwise Distance‡1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ceiling-normalised comparison, EditJumps, two families, 200 references: Positional JS† (× floor)1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ceiling-normalised comparison, EvoFlows published values, six families: Covariance (% of ceiling)1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ceiling-normalised comparison, EvoFlows published values, six families: MIP (% of ceiling)1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ceiling-normalised comparison, EvoFlows published values, six families: Pairwise Distance‡1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ceiling-normalised comparison, EvoFlows published values, six families: Positional JS† (× floor)1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Cell viability drivers versus neutral, default categorical calls (Chen et al. 2020 Additional file 22)17 evaluations · 85 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Cell viability drivers versus neutral, median-score threshold (Chen et al. 2020 Additional file 21)33 evaluations · 165 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Cell-type difference in chromatin contact-map prediction (AlphaGenome paper)2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
cfMethyl-Seq random-split four-cancer detection1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CGC missense oncogenicity, all genes (Lee 2026, OncoCal tool_performance.tsv)49 evaluations · 98 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv)49 evaluations · 98 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CGC missense oncogenicity, tumour suppressors (loss of function) (Lee 2026, OncoCal tool_performance.tsv)49 evaluations · 98 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Chen et al. 2026 continually pretrained clustering, ATAA3 evaluations · 9 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Chen et al. 2026 continually pretrained clustering, BC4 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Chen et al. 2026 continually pretrained clustering, BMMC3 evaluations · 9 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Chen et al. 2026 continually pretrained clustering, HS3 evaluations · 9 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Chen et al. 2026 continually pretrained clustering, ME4 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Chen et al. 2026 continually pretrained clustering, MH4 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Chen et al. 2026 genetic perturbation prediction, Adamson4 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Chen et al. 2026 genetic perturbation prediction, Norman4 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Chen et al. 2026 genetic perturbation prediction, Replogle4 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Chen et al. 2026 supervised cell type annotation, ATAA5 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Chen et al. 2026 supervised cell type annotation, BMMC5 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Chen et al. 2026 supervised cell type annotation, HS5 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Chen et al. 2026 supervised cell type annotation, SEAAD6 evaluations · 36 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Chen et al. 2026 zero-shot cell type and spatial domain clustering, ATAA5 evaluations · 15 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Chen et al. 2026 zero-shot cell type and spatial domain clustering, BC6 evaluations · 18 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Chen et al. 2026 zero-shot cell type and spatial domain clustering, BMMC5 evaluations · 15 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Chen et al. 2026 zero-shot cell type and spatial domain clustering, HS5 evaluations · 15 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Chen et al. 2026 zero-shot cell type and spatial domain clustering, ME6 evaluations · 18 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Chen et al. 2026 zero-shot cell type and spatial domain clustering, MH6 evaluations · 18 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Chen et al. 2026 zero-shot clustering with k-means, ATAA1 evaluation · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Chen et al. 2026 zero-shot clustering with k-means, BC1 evaluation · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Chen et al. 2026 zero-shot clustering with k-means, BMMC1 evaluation · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Chen et al. 2026 zero-shot clustering with k-means, HS1 evaluation · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Chen et al. 2026 zero-shot clustering with k-means, ME1 evaluation · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Chen et al. 2026 zero-shot clustering with k-means, MH1 evaluation · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
chromatin contact-map prediction (AlphaGenome paper)2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
CIViC evidence-direction retrieval, March 20263 evaluations · 162 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CIViC-Fact v3 within-linked-publication passage retrieval, post-cutoff cohort2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Clair3 GPU workflow stage runtimes on HG003 ONT and PacBio WGS (Zheng et al. 2026 Supplementary Table 1)2 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Clathrin independent test: selected-embedding classifiers (clathrin protein classification)13 evaluations · 78 rows6 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
ClinVar in-frame indel pathogenicity, ROC-AUC (Brandes et al. 2023 Fig. 6b, Supplementary Table 2)16 evaluations · 16 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ClinVar missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2)90 evaluations · 180 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ClinVar missense pathogenicity, ESM1b versus EVE on variants scored by both (Brandes et al. 2023 Fig. 2b, Results text)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
ClinVar missense pathogenicity, variants scored by all 19 eligible methods (Brandes et al. 2023 Fig. 2e-f, Supplementary Table 2)19 evaluations · 38 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ClinVar pathogenic versus benign classification from likelihood ratios, AUROC by variant class60 evaluations · 60 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ClinVar pathogenic versus benign SNVs by VEP consequence, AUPRC (AlphaGenome Atlas)10 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)132 evaluations · 132 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ClinVar pathogenic vs benign missense, AUPRC (GPN-Star Supplementary Table 3)8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4)17 evaluations · 34 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ClinVar stop-gain pathogenicity by NMD status, ROC-AUC (Brandes et al. 2023 Fig. 6d, Supplementary Table 2)10 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CLL tumour somatic indels, WGS (Wang et al. 2020 Table S2)12 evaluations · 48 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CLL tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)15 evaluations · 60 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ClusPro BM5 Bound antibody top101 evaluation · 9 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ClusPro BM5 Bound antibody top301 evaluation · 9 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ClusPro BM5 difficult aggregate top101 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ClusPro BM5 difficult aggregate top301 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ClusPro BM5 easy aggregate top101 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ClusPro BM5 easy aggregate top301 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ClusPro BM5 Enzyme top101 evaluation · 11 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ClusPro BM5 Enzyme top301 evaluation · 11 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ClusPro BM5 intermediate aggregate top101 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ClusPro BM5 intermediate aggregate top301 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ClusPro BM5 Others top101 evaluation · 11 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ClusPro BM5 Others top301 evaluation · 11 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ClusPro BM5 Total top101 evaluation · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ClusPro BM5 Total top301 evaluation · 11 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ClusPro BM5 Unbound antibody top101 evaluation · 11 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ClusPro BM5 Unbound antibody top301 evaluation · 11 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CNV calls returned to clinical experts per caller after filtering, Solve-RD exome reanalysis (Demidov et al. 2024 Table 1, Supplementary Table 4)3 evaluations · 63 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5)6 evaluations · 36 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
COACH420, trained on CHEN11 (protein-small molecule binding-site prediction)3 evaluations · 12 rows4 source-scoped figuresChecked result tables available.
Scope and remaining work
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
COLO829 cell line somatic indels, WGS (Wang et al. 2020 Table S2)12 evaluations · 48 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
COLO829 cell line somatic SNVs, WGS (Wang et al. 2020 Table S1)15 evaluations · 60 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
COLO829 tumour-only, indels, AUPRC (Krishnamachari et al. 2026 Supplementary Table 1)9 evaluations · 9 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
COLO829 tumour-only, SNVs, AUPRC (Krishnamachari et al. 2026 Supplementary Table 1)9 evaluations · 9 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Combination phenotype prediction from small training sets: test RMSE at fixed average gene frequency1 evaluation · 60 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Combined K562 CRISPR training pairs, weighted metrics (Gschwind et al. 2026 Supplementary Table 3)6 evaluations · 18 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Composite score S (HyCell report)96 evaluations · 96 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Contacts, CASP14 (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Contacts, CASP15 (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Contacts, ProteinNet (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Coriell virtual gene-panel CNV precision by exon count and length (De La Vega et al. Table 1)2 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Coronary smooth-muscle caQTL effect-size prediction (AlphaGenome paper)3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
COSMIC frequent vs gnomAD common missense, AUPRC (GPN-MSA Supplementary Table 4)17 evaluations · 34 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
COSMIC frequent vs gnomAD common missense, AUPRC (GPN-Star Supplementary Table 3)8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Covariance agreement between natural homologs, 100 references1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Covariance agreement between natural homologs, 20 references1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Covariance agreement between natural homologs, 800 references1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CPPC original Challenge 1 final four-knockout prediction score20 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CPPC original Challenge 2 prospective target ranking score20 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CPPC prospective nomination of desired T-cell states1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CPPC reimplemented best-model Challenge 2 score13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
CPPC screen-1 held-out knockout cell-state proportions0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Cross-atlas annotation transfer, HLCA to Tabula Sapiens, 14 shared cell types (Wu et al. 2025 Table S3)23 evaluations · 46 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Cross-atlas annotation transfer, Tabula Sapiens to HLCA, 14 shared cell types (Wu et al. 2025 Table S2)23 evaluations · 46 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Cryptic splice site activation by rare GT/AG-creating SNVs, GTEx WGS and RNA-seq (SpliceAI2 paper, auPRC)5 evaluations · 17 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Cryptic splice site activation by rare GT/AG-creating variants in Genomics England blood RNA-seq (SpliceAI2 paper, auPRC)5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Cryptic splice site usage among RNA-seq-confirmed GT/AG-creating SNVs, GTEx (SpliceAI2 paper, Spearman)4 evaluations · 16 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Cyclic peptide computational pass rate under cyclisation and TorchScore confidence0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Database storage and classification speed on ONT data, main database (Peres da Silva et al. 2024)6 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Davis drug-target affinity, DeepDTA holdout fold16 evaluations · 32 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Decoded against counted fold change, plasma against naive B (HyCell report)1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DecoNFlow RRBS-CL tumour-fraction limit of detection5 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DecoNFlow RRBS-TT tumour-fraction limit of detection10 evaluations · 60 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DecoNFlow WGBS-TT tumour-fraction limit of detection10 evaluations · 50 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Deep intronic and synonymous variants splicing-based classification (AlphaGenome paper)2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
DeepProtein beta-lactamase (PEER): GPU Memory (GB)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein beta-lactamase (PEER): MAE ↓17 evaluations · 17 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein beta-lactamase (PEER): Time (hour)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein beta-lactamase (PEER): ρ ↑17 evaluations · 17 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Binary localization (PEER): Averaged F1 ↑12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Binary localization (PEER): GPU Memory (GB)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Binary localization (PEER): PR-AUC ↑12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Binary localization (PEER): Time (hour)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein CRISPR-Leenay repair outcome: GPU Memory (GB)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein CRISPR-Leenay repair outcome: MAE ↓11 evaluations · 11 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein CRISPR-Leenay repair outcome: R2 ↑11 evaluations · 11 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein CRISPR-Leenay repair outcome: Time (hour)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Fluorescence (TAPE): GPU Memory (GB)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Fluorescence (TAPE): MAE ↓17 evaluations · 17 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Fluorescence (TAPE): Time (hour)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Fluorescence (TAPE): ρ ↑17 evaluations · 17 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Fold classification (TAPE): Acc ↑9 evaluations · 9 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Fold classification (TAPE): Averaged F1 ↑9 evaluations · 9 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Fold classification (TAPE): GPU Memory (GB)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Fold classification (TAPE): Time (hour)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Human PPI (PEER): Averaged F1 ↑11 evaluations · 11 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Human PPI (PEER): GPU Memory (GB)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Human PPI (PEER): PR-AUC ↑11 evaluations · 11 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Human PPI (PEER): Time (hour)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein IEDB epitope prediction: Averaged F1 ↑3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein IEDB epitope prediction: ROC-AUC ↑3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein PDB-Jespersen epitope prediction: Averaged F1 ↑3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein PDB-Jespersen epitope prediction: ROC-AUC ↑3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein PPI affinity (PEER): GPU Memory (GB)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein PPI affinity (PEER): MAE ↓11 evaluations · 11 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein PPI affinity (PEER): R2 ↑11 evaluations · 11 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein PPI affinity (PEER): Time (hour)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein SAbDab-Chen antibody developability: GPU Memory (GB)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein SAbDab-Chen antibody developability: MAE ↓11 evaluations · 11 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein SAbDab-Chen antibody developability: R2 ↑11 evaluations · 11 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein SAbDab-Chen antibody developability: Time (hour)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein SAbDab-Liberis paratope prediction: Averaged F1 ↑3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein SAbDab-Liberis paratope prediction: ROC-AUC ↑3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Secondary structure prediction (TAPE): Acc ↑3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Secondary structure prediction (TAPE): Averaged F1 ↑3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Solubility (PEER): Averaged F1 ↑17 evaluations · 17 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Solubility (PEER): GPU Memory (GB)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Solubility (PEER): PR-AUC ↑17 evaluations · 17 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Solubility (PEER): Time (hour)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Stability (TAPE): GPU Memory (GB)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Stability (TAPE): MAE ↓17 evaluations · 17 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Stability (TAPE): Time (hour)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Stability (TAPE): ρ ↑17 evaluations · 17 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Subcellular localization (PEER): Acc ↑12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Subcellular localization (PEER): Averaged F1 ↑12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Subcellular localization (PEER): GPU Memory (GB)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Subcellular localization (PEER): Time (hour)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein TAP antibody developability: GPU Memory (GB)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein TAP antibody developability: MAE ↓11 evaluations · 11 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein TAP antibody developability: R2 ↑11 evaluations · 11 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein TAP antibody developability: Time (hour)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Yeast PPI (PEER): Averaged F1 ↑11 evaluations · 11 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Yeast PPI (PEER): GPU Memory (GB)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Yeast PPI (PEER): PR-AUC ↑11 evaluations · 11 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepProtein Yeast PPI (PEER): Time (hour)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepRVAT rare variant association testing, replicated genes (GPN-Star Fig. 2j)2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepRVAT rare variant association testing, significant genes (GPN-Star Fig. 2j)2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DeepVariant execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1)11 evaluations · 42 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DEKOIS 2.0 screening by rescoring AF3-predicted complexes (Shen et al. 2025 Table 2, AF3 block)10 evaluations · 100 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DEKOIS 2.0 screening by rescoring Protenix-predicted complexes (Shen et al. 2025 Table 2, Protenix block)13 evaluations · 130 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DEKOIS 2.0 screening with co-folding confidence scores against docking tools (Shen et al. 2025 Table 1)24 evaluations · 240 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DELFI 2019 internally cross-validated cancer detection protocol1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Depletion of high-scoring splice-proximal SNVs in gnomAD, TOPMed and UK Biobank, high-pLI genes (SpliceAI2 paper, Spearman)4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Detection of 16 known pathogenic splicing events in clinical muscle RNA-seq (Segarra-Casas et al. Table 2)5 evaluations · 80 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Detection of RT-PCR-positive viruses per sample, with assigned read counts (de Vries et al. 2021 Supplementary Table 2)13 evaluations · 221 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Diagnostic sensitivity, day 0 or 1 (Wolf et al. 2026 Table 2)1 evaluation · 18 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DNA language model inference throughput and maximum batch size on one A100 80 GB by sequence length (Aspidova et al. 2026 Table 2)9 evaluations · 92 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DNALONGBENCH Contact map prediction (Table 4)5 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DNALONGBENCH Enhancer-target gene prediction (Table 3)5 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DNALONGBENCH Expression quantitative trait loci prediction (Table 7)5 evaluations · 50 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DNALONGBENCH Regulatory sequence activity prediction (Table 5)5 evaluations · 15 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DNALONGBENCH Transcription initiation signal prediction (Table 6)5 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DNase prediction on held-out peaks (AlphaGenome paper)2 evaluations · 6 rows3 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
DNase track prediction at 128 bp (AlphaGenome paper)3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
DNase track prediction at 32 bp (AlphaGenome paper)2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
DNM1 minigene screen, active versus inactive variants, average precision (AlphaGenome Atlas)8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Docking score of designed ligand pockets0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
DREAM synthetic set 1 somatic SNVs, WGS (Wang et al. 2020 Table S1)15 evaluations · 60 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DREAM synthetic set 2 somatic SNVs, WGS (Wang et al. 2020 Table S1)15 evaluations · 60 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DREAM synthetic set 3 somatic indels, WGS (Wang et al. 2020 Table S2)12 evaluations · 48 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DREAM synthetic set 3 somatic SNVs, WGS (Wang et al. 2020 Table S1)15 evaluations · 60 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DREAM synthetic set 4 somatic indels, WGS (Wang et al. 2020 Table S2)12 evaluations · 48 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
DREAM synthetic set 4 somatic SNVs, WGS (Wang et al. 2020 Table S1)15 evaluations · 60 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Driver fusions, conventional RNA-seq of haematologic cell lines, validated truth (Tamura et al. 2026 Supplementary Table 5)12 evaluations · 72 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Driver fusions, targeted RNA-seq of haematologic cell lines, validated truth (Tamura et al. 2026 Supplementary Table 5)12 evaluations · 72 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
E. coli sigma70 independent promoter test (E. coli sigma70 promoter prediction)15 evaluations · 60 rows4 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
EC classification (DGEB) (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
EC, DeepFRI split (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
EC, SaProt split (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
EditJumps frame with the reference alignment expanded to 800 homologs: spectrum MMD0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
EditJumps section 4.2 frame, 200 references: cov. agr.12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
EditJumps section 4.2 frame, 200 references: edits12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
EditJumps section 4.2 frame, 200 references: JS pos.12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
EditJumps section 4.2 frame, 200 references: KL pool.12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
EditJumps section 4.2 frame, 200 references: KL pos.12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
EditJumps section 4.2 frame, 200 references: MIP agr.12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
EditJumps section 4.2 frame, 200 references: MMD12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
EditJumps section 4.2 frame, 200 references: pairw. Lev.12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
EditJumps section 4.2 frame, 200 references: prof. LL8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
EditJumps section 4.2 frame, 200 references: ΔH12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Embedding throughput on one NVIDIA H20 (HyPLM report)1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ENCODE4 within-donor organ pairs, Pearson r of predicted against measured isoform change4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Enformer CAGE gene-expression comparison2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Enformer CAGE gene-expression comparison Across genes CAGE Pearson: Mean across-experiment Pearson correlation of human test-gene CAGE expression2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
EnFusion undiluted Seraseq duplicate benchmark4 evaluations · 16 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ENIGMA specification pilot resolution1 evaluation · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Enzyme-pair functional identity: original held-out test (Enzyme functional identity prediction)5 evaluations · 40 rows8 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
eQTL effect direction (AlphaGenome paper)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • Reported scores remain quarantined because the supplementary table and another source disagree; see the protocol limitations for the exact discrepancy.
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
eQTL effect-size ranking (AlphaGenome paper)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • Reported scores remain quarantined because the supplementary table and another source disagree; see the protocol limitations for the exact discrepancy.
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
ESMFold2 Runs N’ Poses reported comparison msa: Runs N’ Poses ligand pass rate (MSA)7 evaluations · 7 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ESMFold2 Runs N’ Poses reported comparison single-sequence: Runs N’ Poses ligand pass rate (single sequence)4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
European-ancestry LCL caQTL classification (AlphaGenome paper)3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
European-ancestry LCL caQTL effect-size prediction (AlphaGenome paper)3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
EVEE ClinVar indel pathogenicity AUROC (Pearce et al. 2026 Figure 1d)4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
EVEE deconfounded ClinVar SNV pathogenicity AUROC (Pearce et al. 2026 Figure 1c)8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
EVEE Evo 2 embedding extraction compute (Pearce et al. 2026)1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Evo 2 7B BRCA1 variant scoring throughput on one GPU (evo2-cloud-operations W1)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
EvoFlows published values, two families: diversity12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
EvoFlows published values, two families: edits/seq12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
EvoFlows published values, two families: KL x10^312 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
EvoFlows published values, two families: MMD12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Excess panel-matched rare variants in Genomics England rare-disease probands at panel-match odds ratio 2 (SpliceAI2 paper)1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Exomiser rank-budget recovery in ACG trios1 evaluation · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Exon-level CNV detection in clinical exomes against CMA truth, after removing tool-specific problematic regions (Hwang et al. Table 4, post-filter)4 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Exon-level CNV detection in clinical exomes against CMA truth, default calls (Hwang et al. Table 4, pre-filter)4 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
False positives in seven pathogen-free libraries (Tisza et al. 2026 Table S6)5 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FAS exon 6 saturation MPSA: transcriptome-normalised sensitivity at a 10% background call rate (Smith and Kitzman Table S2)8 evaluations · 16 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FASTQ-to-VCF runtime, core-hours and Azure cost of three Sentieon DNAscope pipelines on one 120-vCPU instance (Hu et al. 2026 Table 2)3 evaluations · 21 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng A.Thaliana 4mC sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Acceptor sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng C.Elegans 4mC sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Coding sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng D.Melanogaster 4mC sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng DNase I Hypersensitive sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Donor sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng E.Coli 4mC sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Enhancer Cohn sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Enhancer Ensembl sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Enhancer sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng eQTL discrimination24 evaluations · 60 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng G.Pickeringii 4mC sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng G.Subterraneus 4mC sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng GTEx whole-blood expression prediction, 768 genes, long input3 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng GTEx whole-blood expression prediction, all genes, 6 kb input5 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Human 5mC sequence classification3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Human 6 mA sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Human TFBS 1 sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Human TFBS 2 sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Human TFBS 3 sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Human TFBS 4 sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Human TFBS 5 sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Human vs worm sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng ipaQTL discrimination24 evaluations · 60 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Mouse TFBS 1 sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Mouse TFBS 2 sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Mouse TFBS 3 sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Mouse TFBS 4 sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Mouse TFBS 5 sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Open chromatin region sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng paQTL discrimination24 evaluations · 60 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng pathogenic-versus-common SNP classification22 evaluations · 55 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Promoter All 300 bps sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Promoter All 70 bps sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Promoter Arabidopsis NonTATA sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Promoter Arabidopsis TATA sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Promoter B.Amyloliquefaciens sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Promoter GM12878 sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Promoter Hela-S3 sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Promoter HUVEC sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Promoter NHEK sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Promoter NonTATA 251 bps sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Promoter NonTATA 300 bps sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Promoter NonTATA 70 bps sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Promoter R.Capsulatus sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Promoter TATA 300 bps sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Promoter TATA 70 bps sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng sQTL discrimination24 evaluations · 60 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng TAD recognition from NT-v2 attention0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Feng Yeast H3 sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Yeast H3K14ac sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Yeast H3K36me3 sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Yeast H3K4me1 sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Yeast H3K4me2 sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Yeast H3K4me3 sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Yeast H3K79me3 sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Yeast H3K9ac sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Yeast H4 sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Feng Yeast H4ac sequence classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FEP+ benchmark four-target subset, affinity ranking and cost10 evaluations · 100 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FEP+ benchmark OpenFE subset, affinity ranking6 evaluations · 54 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Fine-tuning and evaluation wall time, 5 epochs on the Enformer eQTL dataset (Hegde et al. 2025 Table A1)1 evaluation · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Fine-tuning wall time to convergence on the Enformer eQTL dataset (Hegde et al. 2025 Methods)2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Fingerprint prediction from MS/MS, MassSpecGym random split, assumption (1) (Khoo 2026)5 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Fingerprint prediction from MS/MS, MassSpecGym random split, assumption (2) (Khoo 2026)5 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Fingerprint prediction from MS/MS, MassSpecGym random split, assumption (3) (Khoo 2026)6 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Fingerprint prediction from MS/MS, MassSpecGym scaffold split, assumption (1) (Khoo 2026)5 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Fingerprint prediction from MS/MS, MassSpecGym scaffold split, assumption (2) (Khoo 2026)5 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Fingerprint prediction from MS/MS, MassSpecGym scaffold split, assumption (3) (Khoo 2026)6 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Fingerprint prediction from MS/MS, NPLIB1 random split, assumption (1) (Khoo 2026)5 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Fingerprint prediction from MS/MS, NPLIB1 random split, assumption (2) (Khoo 2026)5 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Fingerprint prediction from MS/MS, NPLIB1 random split, assumption (3) (Khoo 2026)6 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Fingerprint prediction from MS/MS, NPLIB1 scaffold split, assumption (1) (Khoo 2026)5 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Fingerprint prediction from MS/MS, NPLIB1 scaffold split, assumption (2) (Khoo 2026)5 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Fingerprint prediction from MS/MS, NPLIB1 scaffold split, assumption (3) (Khoo 2026)6 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Fireprot homologue-free split ddG prediction (Dieckhaus et al. 2024 Table 2)12 evaluations · 36 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Flagging new reanalysis candidates from Exomiser score changes across database releases (Vestito et al. 2024 Supplementary Table 1)81 evaluations · 648 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FlexMS molecule-to-spectrum prediction on MassSpecGym, embedder-predictor grid (Table 2)33 evaluations · 66 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP2 Amylase by-mutation; held-out test set · Amylase9 evaluations · 18 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP2 Amylase close-to-far; held-out test set · Amylase9 evaluations · 17 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP2 Amylase far-to-close; held-out test set · Amylase9 evaluations · 18 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP2 Amylase one-to-many; held-out test set · Amylase9 evaluations · 18 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP2 hydro low-to-high; held-out test set · hydro9 evaluations · 18 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP2 hydro three-to-many; held-out test set · hydro9 evaluations · 18 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP2 hydro to-P01053; held-out test set · hydro9 evaluations · 17 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP2 hydro to-P06241; held-out test set · hydro9 evaluations · 18 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP2 hydro to-P0A9X9; held-out test set · hydro9 evaluations · 18 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP2 IRED two-to-many; held-out test set · IRED9 evaluations · 18 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP2 NucB two-to-many; held-out test set · NucB9 evaluations · 18 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP2 PDZ3 single-to-double; held-out test set · PDZ39 evaluations · 17 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP2 Rhomax by_wild_type5 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP2 rhomax by-wild-type; held-out test set · rhomax9 evaluations · 17 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP2 TrpB by-position; held-out test set · TrpB9 evaluations · 18 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP2 TrpB one-to-many; held-out test set · TrpB9 evaluations · 17 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FLIP2 TrpB two-to-many; held-out test set · TrpB9 evaluations · 18 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Fluorescence (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FoldBench antibody-antigen published full-set assessment5 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FoldBench dna-monomer published full-set assessment5 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FoldBench protein-dna published full-set assessment5 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FoldBench protein-ligand published full-set assessment5 evaluations · 15 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FoldBench protein-monomer published full-set assessment5 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FoldBench protein-peptide published full-set assessment5 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FoldBench protein-protein published full-set assessment5 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FoldBench protein-rna published full-set assessment5 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FoldBench rna-monomer published full-set assessment5 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Fragmentia-AI paper: ULP-WGS cancer vs non-cancer AUC on a held-out validation set, six feature sets x three classifiers19 evaluations · 19 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Fragmentia-AI WGS paper: External DELFI cohort (FinaleDB)1 evaluation · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Fragmentia-AI WGS paper: Independent test cohort by ichorCNA tumour fraction1 evaluation · 11 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Fragmentia-AI WGS paper: Internal validation cohort by ichorCNA tumour fraction3 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Fragmentia-AI WGS paper: Training cohort (resubstitution)2 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FramePool study MRL: Human 25-100nt5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FramePool study MRL: Human 50nt5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FramePool study MRL: Random 25-100nt10 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FramePool study MRL: Random 50nt10 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
FRASER Kremer cohort known pathogenic-event subsampling1 evaluation · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Frozen project benchmark Atomic Motif Enzyme, fixed ligand: distinct passers per GPU-hour2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Frozen project benchmark DNA binding, fixed DNA: distinct passers per GPU-hour1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Frozen project benchmark DNA binding, unfixed DNA: distinct passers per GPU-hour1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Frozen project benchmark protein binding, all-atom conditioning: distinct passers per GPU-hour1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Frozen project benchmark protein binding, backbone conditioning: distinct passers per GPU-hour1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Frozen project benchmark small-molecule binding, unfixed ligand: distinct passers per GPU-hour2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Gain in scTM at fixed diversity from reinforcement learning (HyInv report)1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Gain in scTM at fixed diversity over the unmodified sampler (HyInv report)12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
gamma-delta T against tissue-resident CD8 T split, ARI (HyCell report)2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GB1 low-vs-high (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GB1 three-vs-rest (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GB1 two-vs-rest (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GEARS Norman2019 CPA-control comparison4 evaluations · 8 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GEARS Norman2019 CPA-control comparison MSE: Norman2019 perturbation-response MSE4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GEARS Norman2019 CPA-control comparison Pearson DE: Norman2019 perturbation-response Pearson DE4 evaluations · 4 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Bulk RNA expression5 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Coding vs Intergenomic7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Drosophila enhancer activity (dev)6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Drosophila enhancer activity (hk)6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Drosophila enhancer activity (Mean)6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Genomic structure prediction (H1-ESC)6 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Genomic structure prediction (HFF)6 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Human Core Promoter Detection7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Human Core Promoter Detection, dataset all7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Human Core Promoter Detection, dataset notata7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Human Core Promoter Detection, dataset tata7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Human Enhancers Cohn7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Human Enhancers Ensembl7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Human Ensembl Regulatory7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Human Nontata Promoters7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Human OCR Ensembl7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Human Promoter Detection7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Human Promoter Detection, dataset all7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Human Promoter Detection, dataset notata7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Human Promoter Detection, dataset tata7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Human Splice Site Detection7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Human Transcription Factor Prediction7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Human Transcription Factor Prediction, dataset 07 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Human Transcription Factor Prediction, dataset 17 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Human Transcription Factor Prediction, dataset 27 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Human Transcription Factor Prediction, dataset 37 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Human Transcription Factor Prediction, dataset 47 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Human vs Worm7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Long-range Promoters Prediction5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Long-range Species Classification5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Long-range splice site prediction (Mean)6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Long-range splice site prediction (Splice acceptor)6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Long-range splice site prediction (Splice donar)6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Mouse Enhancers7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Mouse Transcription Factor Prediction7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Mouse Transcription Factor Prediction, dataset 07 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Mouse Transcription Factor Prediction, dataset 17 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Mouse Transcription Factor Prediction, dataset 27 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Mouse Transcription Factor Prediction, dataset 37 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Mouse Transcription Factor Prediction, dataset 47 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Virus Covid Variant Classification7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Yeast Epigenetic Marks Prediction7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Yeast Epigenetic Marks Prediction, dataset H37 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Yeast Epigenetic Marks Prediction, dataset H3K14ac7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Yeast Epigenetic Marks Prediction, dataset H3K36me37 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Yeast Epigenetic Marks Prediction, dataset H3K4me17 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Yeast Epigenetic Marks Prediction, dataset H3K4me27 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Yeast Epigenetic Marks Prediction, dataset H3K4me37 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Yeast Epigenetic Marks Prediction, dataset H3K79me37 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Yeast Epigenetic Marks Prediction, dataset H3K9ac7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Yeast Epigenetic Marks Prediction, dataset H47 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenBench Yeast Epigenetic Marks Prediction, dataset H4ac7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Gene region classification from averaged GPN embeddings, leave-one-chromosome-out1 evaluation · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Gene-level logistic regression under 5-fold GroupKFold by perturbation (Kendiukhov 2026)7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Gene-MTEB genomic embedding benchmark HMPD-disease: HMPD-disease genomic embedding evaluation5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Gene-MTEB genomic embedding benchmark HMPD-sex: HMPD-sex genomic embedding evaluation5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Gene-MTEB genomic embedding benchmark HMPD-single: HMPD-single genomic embedding evaluation5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Gene-MTEB genomic embedding benchmark HMPD-source: HMPD-source genomic embedding evaluation5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Gene-MTEB genomic embedding benchmark HMPR-p2p: HMPR-p2p genomic embedding evaluation5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Gene-MTEB genomic embedding benchmark HMPR-s2s-align: HMPR-s2s-align genomic embedding evaluation5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Gene-MTEB genomic embedding benchmark HMPR-s2s-small: HMPR-s2s-small genomic embedding evaluation5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Gene-MTEB genomic embedding benchmark HMPR-s2s-tiny: HMPR-s2s-tiny genomic embedding evaluation5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Gene-MTEB genomic embedding benchmark Human-Virus-1: Human-Virus-1 genomic embedding evaluation5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Gene-MTEB genomic embedding benchmark Human-Virus-2: Human-Virus-2 genomic embedding evaluation5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Gene-MTEB genomic embedding benchmark Human-Virus-3: Human-Virus-3 genomic embedding evaluation5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Gene-MTEB genomic embedding benchmark Human-Virus-4: Human-Virus-4 genomic embedding evaluation5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Gene-MTEB genomic embedding benchmark HVR-p2p: HVR-p2p genomic embedding evaluation5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Gene-MTEB genomic embedding benchmark HVR-s2s-align: HVR-s2s-align genomic embedding evaluation5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Gene-MTEB genomic embedding benchmark HVR-s2s-small: HVR-s2s-small genomic embedding evaluation5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Gene-MTEB genomic embedding benchmark HVR-s2s-tiny: HVR-s2s-tiny genomic embedding evaluation5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Gene-program consistency across donors, classical to nonclassical monocytes (HyCell report)2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Gene-program consistency across donors, naive B to plasma cells (HyCell report)2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Gene-program consistency across donors, naive to effector CD4 T cells (HyCell report)2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GENEB leaderboard, 1-shot, MCC aggregates41 evaluations · 615 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GENEB leaderboard, 10-shot, MCC aggregates41 evaluations · 615 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GENEB leaderboard, full training data, MCC aggregates41 evaluations · 615 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3)6 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Genie 3 short monomer generation designability: Unconditional short monomer Designability13 evaluations · 13 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Genie 3 short monomer generation diversity-tm-05: Unconditional short monomer Diversity, TM < 0.513 evaluations · 13 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Genie 3 short monomer generation diversity-tm-06: Unconditional short monomer Diversity, TM < 0.613 evaluations · 13 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Genie 3 short monomer generation novelty-afdb: Unconditional short monomer Novelty, AFDB13 evaluations · 13 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Genie 3 short monomer generation novelty-pdb: Unconditional short monomer Novelty, PDB13 evaluations · 13 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Genome-wide prophage detection (Genome-wide prophage detection)17 evaluations · 102 rows6 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
GenomeOcean embedding extraction throughput, peak VRAM and binning fidelity, BF16 versus FP8 weights (Yu et al. 2026 Table 3)6 evaluations · 21 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GenomeOcean-4B autoregressive generation throughput, power, energy efficiency and perplexity, BF16 versus FP8 (Yu et al. 2026 Table 4)3 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Genus-level read classification of ONT bacterial isolates, main database (Peres da Silva et al. 2024)3 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Germline FASTQ-to-VCF runtime by read depth, Parabricks v4.3.0 on V100 and A100 GPUs versus the CPU GATK equivalent (Marangoni et al. 2026 Table S1)4 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API Bend Variant Effects Disease, zs-ar-llr1 evaluation · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API Bend Variant Effects Disease, zs-embedding5 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API Bend Variant Effects Disease, zs-mlm-llr4 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API Bend Variant Effects Expression, zs-ar-llr1 evaluation · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API Bend Variant Effects Expression, zs-embedding5 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API Bend Variant Effects Expression, zs-mlm-llr4 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API BRCA1, zs-ar-llr1 evaluation · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API BRCA1, zs-embedding5 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API BRCA1, zs-mlm-llr4 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API ClinVar Indel Pathogenicity, zs-ar-llr1 evaluation · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API ClinVar Indel Pathogenicity, zs-embedding5 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API GUE Promoter All, supervised5 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API GUE Splice Site, supervised5 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API GUE Transcription Factor, supervised5 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API LOL-EVE, zs-ar-llr1 evaluation · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API LOL-EVE, zs-embedding5 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API LRB Variant Effect Causal eQTL, supervised5 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API LRB Variant Effect OMIM, zs-ar-llr1 evaluation · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API LRB Variant Effect OMIM, zs-embedding5 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API LRB Variant Effect OMIM, zs-mlm-llr4 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API Songlab ClinVar, zs-ar-llr1 evaluation · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API Songlab ClinVar, zs-embedding5 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API Songlab ClinVar, zs-mlm-llr4 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API TraitGym Complex, zs-ar-llr1 evaluation · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API TraitGym Complex, zs-embedding5 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API TraitGym Complex, zs-mlm-llr4 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API TraitGym Mendelian, zs-ar-llr1 evaluation · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API TraitGym Mendelian, zs-embedding5 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API TraitGym Mendelian, zs-mlm-llr4 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API Var Bench Coding Pathogenicity, supervised5 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API Var Bench Common Vs Rare, supervised5 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API Var Bench Expression, supervised5 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API Var Bench meQTL, supervised5 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API Var Bench Non Coding Pathogenicity, supervised5 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API Var Bench sQTL, supervised4 evaluations · 16 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API VEP-eval, zs-embedding4 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GFMBench-API VEP-eval, zs-mlm-llr4 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GlycanML class Accuracy: GlycanGT study: class Accuracy5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GlycanML class Macro-F1: GlycanGT study: class Macro-F15 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GlycanML domain Accuracy: GlycanGT study: domain Accuracy5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GlycanML domain Macro-F1: GlycanGT study: domain Macro-F15 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GlycanML family Accuracy: GlycanGT study: family Accuracy5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GlycanML family Macro-F1: GlycanGT study: family Macro-F15 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GlycanML genus Accuracy: GlycanGT study: genus Accuracy5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GlycanML genus Macro-F1: GlycanGT study: genus Macro-F15 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GlycanML glycosylation Accuracy: GlycanGT study: glycosylation Accuracy5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GlycanML glycosylation Macro-F1: GlycanGT study: glycosylation Macro-F15 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GlycanML immunogenicity Accuracy: GlycanGT study: immunogenicity Accuracy5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GlycanML immunogenicity AUPRC: GlycanGT study: immunogenicity AUPRC5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GlycanML immunogenicity Macro-F1: GlycanGT study: immunogenicity Macro-F13 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GlycanML kingdom Accuracy: GlycanGT study: kingdom Accuracy5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GlycanML kingdom Macro-F1: GlycanGT study: kingdom Macro-F15 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GlycanML order Accuracy: GlycanGT study: order Accuracy5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GlycanML order Macro-F1: GlycanGT study: order Macro-F15 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GlycanML phylum Accuracy: GlycanGT study: phylum Accuracy5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GlycanML phylum Macro-F1: GlycanGT study: phylum Macro-F15 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GlycanML species Accuracy: GlycanGT study: species Accuracy5 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GlycanML species Macro-F1: GlycanGT study: species Macro-F15 evaluations · 5 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GlyConnect glycosylation · Glycos (GlycanML glycosylation type prediction)10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Paper table does not enumerate trained checkpoint hashes; source configuration names retained.
gnomAD rare versus common enrichment in the deleterious tail, odds ratio (GPN-Star Fig. 4b)12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
gnomAD rare vs common enrichment in the deleterious tail, odds ratio (GPN-MSA Supplementary Table 4)17 evaluations · 34 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GO-BP (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GO-CC (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GO-MF (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GPCRrecent screening (16 GPCR targets) (Shen et al. 2025 Table 3)14 evaluations · 140 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GPCRrecent screening (the six targets whose first structures postdate the Boltz-2 training cutoff) (Shen et al. 2025 Table 3)2 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GREGoR solved cases, recall of causal variants in the top 50 per patient (AlphaGenome Atlas)4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GTEx tissue-specific splicing prediction, Splice acceptors and donors (You et al. 2026 Supplementary Table 5)8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GTEx tissue-specific splicing prediction, Splice-15class (You et al. 2026 Supplementary Table 5)7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GTEx tissue-specific splicing prediction, Splice-53class (You et al. 2026 Supplementary Table 5)7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GTEx v8 fine-mapped sQTL effect size prediction (SpliceAI2 paper, Spearman)4 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GTEx v8 fine-mapped sQTL SNVs against non-prioritised SNVs near junction ends (SpliceAI2 paper, auROC)4 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUANinE v1.1 cadd-snv, Spearman rho x100 (Table 3)23 evaluations · 23 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUANinE v1.1 ccre-propensity, Spearman rho x100 (Table 2)32 evaluations · 32 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUANinE v1.1 clinvar-snv, Spearman rho x100 (Table 4)12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUANinE v1.1 cons100, Spearman rho x100 (Table 2)32 evaluations · 32 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUANinE v1.1 cons30, Spearman rho x100 (Table 2)32 evaluations · 32 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUANinE v1.1 dnase-propensity, Spearman rho x100 (Table 2)32 evaluations · 32 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUANinE v1.1 gpra-c, Spearman rho x100 (Table 2)31 evaluations · 31 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GUANinE v1.1 gpra-d, Spearman rho x100 (Table 2)31 evaluations · 31 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
GWAS hit enrichment in the lowest 1% of scores, AraGWAS permutation threshold1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HaplotypeCaller execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1)11 evaluations · 42 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HECTOR vs. ENIGMA Evidence Repository (eRepo) agreement1 evaluation · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Held-out CRISPR enhancer-gene benchmark, weighted metrics, five cell types (Gschwind et al. 2026 Supplementary Table 3)6 evaluations · 18 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Held-out human-versus-virus protein classification (human-versus-viral protein classification)8 evaluations · 32 rows4 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
Held-out trials, immunotherapy response AUROC, equal mean over six trials10 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Held-out trials, OS hazard ratio of higher- against lower-risk half, geometric mean over six trials7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Held-out trials, OS Uno C-index weighted by trial size, TCGA plus non-trial cohorts plus other trials training pool3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Held-out trials, PFS hazard ratio of higher- against lower-risk half, geometric mean over three trials7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Helzer et al. 2025 Razavi et al. 2019 GRAIL cohort, FoundationOne Liquid CDx gene subset: multinomial phenotype AUROC13 evaluations · 65 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Helzer et al. 2025 Razavi et al. 2019 GRAIL cohort, full panel: multinomial phenotype AUROC13 evaluations · 65 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Helzer et al. 2025 Razavi et al. 2019 GRAIL cohort, Guardant360 CDx gene subset: multinomial phenotype AUROC13 evaluations · 65 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Helzer et al. 2025 Razavi et al. 2019 GRAIL cohort, Tempus xF gene subset: multinomial phenotype AUROC13 evaluations · 65 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Helzer et al. 2025 UW cohort, FoundationOne Liquid CDx gene subset: multinomial phenotype AUROC13 evaluations · 130 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Helzer et al. 2025 UW cohort, full panel: multinomial phenotype AUROC14 evaluations · 140 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Helzer et al. 2025 UW cohort, Guardant360 CDx gene subset: multinomial phenotype AUROC13 evaluations · 130 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Helzer et al. 2025 UW cohort, Tempus xF gene subset: multinomial phenotype AUROC13 evaluations · 130 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HG002 DRAGEN full single-genome runtime on Phase41 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HG002 exon-overlap CNV benchmark by event type and length (De La Vega et al. Table S3)8 evaluations · 176 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HG002 GIAB v0.6 CNV deletion [10,000-20,0000) bp (DRAGEN Table S4)3 evaluations · 9 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HG002 GIAB v0.6 CNV deletion [20,000-50,000) bp (DRAGEN Table S4)3 evaluations · 9 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HG002 GIAB v0.6 CNV deletion [5,000-10,000) bp (DRAGEN Table S4)3 evaluations · 9 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HG002 GIAB v0.6 CNV deletion >50,000 bp (DRAGEN Table S4)3 evaluations · 9 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HG002 GIAB v0.6 CNV deletion 1–5kb F-score3 evaluations · 9 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HG002 short-read deletion calling by length bin, witty.er (Nardone et al. Table S1)10 evaluations · 240 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HG003 ONT WGS small-variant accuracy against GIAB v4.2.1, Clair3 versus DeepVariant (Zheng et al. 2026 Supplementary Table 3)3 evaluations · 135 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HG003 ONT WGS variant-calling runtime, memory and I/O, Clair3 versus DeepVariant in GPU mode (Zheng et al. 2026 Supplementary Table 2)2 evaluations · 40 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HG003 PacBio Revio WGS small-variant accuracy against GIAB v4.2.1, Clair3 versus DeepVariant (Zheng et al. 2026 Supplementary Table 3)3 evaluations · 135 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HG003 PacBio Revio WGS variant-calling runtime, memory and I/O, Clair3 versus DeepVariant in GPU mode (Zheng et al. 2026 Supplementary Table 2)2 evaluations · 40 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HG008 all-benchmark region (sensitivity analysis), SNVs and indels combined, Mutect2, Strelka2, DeepSomatic and ensembles (Hasan 2026 Table 4)6 evaluations · 36 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HG008 primary region (nogermlineinterference), indels, Mutect2, Strelka2, DeepSomatic and ensembles (Hasan 2026 Table 2, Class 'INDEL')6 evaluations · 36 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HG008 primary region (nogermlineinterference), SNVs and indels combined, Mutect2, Strelka2, DeepSomatic and ensembles (Hasan 2026 Table 1)6 evaluations · 36 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HG008 primary region (nogermlineinterference), SNVs, Mutect2, Strelka2, DeepSomatic and ensembles (Hasan 2026 Table 2, Class 'SNV')6 evaluations · 36 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HGMD pathogenic vs gnomAD common regulatory variants, AUPRC (GPN-Star Supplementary Table 3)8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HGMD/gnomAD missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2)90 evaluations · 180 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HGMD/gnomAD missense pathogenicity, ESM1b versus EVE on variants scored by both (Brandes et al. 2023 Fig. 2b, Results text)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
HGMD/gnomAD missense pathogenicity, variants scored by all 19 eligible methods (Brandes et al. 2023 Fig. 2e-f, Supplementary Table 2)19 evaluations · 38 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HiFi ATCC MSA-1003 mock community (PacBio Sequel II HiFi): species detection at 0.001% of total reads (Portik et al. 2022 Table 4)14 evaluations · 112 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HiFi ZymoBIOMICS D6331 gut microbiome standard (PacBio Sequel II HiFi): species detection at 0.001% of total reads (Portik et al. 2022 Table 4)14 evaluations · 112 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
histone ChIP-seq track prediction at 128 bp (AlphaGenome paper)3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
histone ChIP-seq track prediction at 32 bp (AlphaGenome paper)2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
Hou et al. 2024 Cristiano cohort cross-validation, pan-cancer and seven cancer types (Table S2)10 evaluations · 220 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Hou et al. 2024 independent validation, Mathios et al. independent lung cohort (Table S3)10 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Hou et al. 2024 independent validation, Mathios et al. LUCAS cohort (Table S3)10 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Hou et al. 2024 independent validation, Zhou et al. liver cancer cohort (Table S3)10 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Hou et al. 2024 Jiang cohort cross-validation, liver cancer (Table S2)10 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Hou et al. 2024 pan-cancer vs healthy, Cristiano cohort, 10 x 10-fold cross-validation (Table 1 AUC)25 evaluations · 25 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
How well ipTM tracks DockQ on cognate nanobody-antigen complexes3 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Hu 2026 BRCA2 functional-integration classification yield1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Huh7 recovery of 34 previously reported fusions by library type, union of callers (Dorney et al. 2026)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Human RNA 2OMe sites, five-fold cross-validation (human RNA 2-prime-O-methylation site prediction)7 evaluations · 49 rows7 source-scoped figuresChecked result tables available.
Scope and remaining work
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
Human RNA 2OMe sites, independent test set (human RNA 2-prime-O-methylation site prediction)5 evaluations · 35 rows7 source-scoped figuresChecked result tables available.
Scope and remaining work
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
Human splice-junction classification and count prediction (AlphaGenome paper)2 evaluations · 4 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
Human splice-site classification: annotation-derived (AlphaGenome paper)3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
Human splice-site classification: RNA-derived (AlphaGenome paper)3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
Human splice-site usage (AlphaGenome paper)3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
HumanPPI (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HuRI PPI link prediction, Accuracy (Table 6)77 evaluations · 77 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HuRI PPI link prediction, Hits@100 (Table 5)77 evaluations · 77 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Hydrolase to P06241 (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
HyInv above the ProteinMPNN temperature curve at HyInv's diversity (HyInv report)2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Identify all pathogens and the causal pathogen in one clinical blood metagenome (CAMI II clinical pathogen challenge)8 evaluations · 16 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Illumina ATCC MSA-1003 mock community (HiSeq 2500): species detection at 0.001% of total reads (Portik et al. 2022 Table 4)7 evaluations · 56 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Illumina COLO829 tumour-only, 50x, somatic indels (Chen et al. 2025 Supplementary Table 7b)6 evaluations · 42 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Illumina COLO829 tumour-only, 50x, somatic SNVs (Chen et al. 2025 Supplementary Table 7b)6 evaluations · 42 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Illumina ZymoBIOMICS D6300 standard (NovaSeq 6000), subsampled: species detection at 0.001% of total reads (Portik et al. 2022 Table 4)7 evaluations · 56 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
In vitro activity of Evo-generated mobile-element designs (Nguyen et al. 2024)2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Independent replication of 1-gene perturbation design: cumulative hits after 5 rounds of 128 genes55 evaluations · 55 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
INSR isoform split in TCGA stomach tumours, mean absolute error3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
INSR isoform split in TCGA stomach tumours, Pearson r2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Isoform variation in eight held-out TCGA cancer types, median Pearson r over gene and cancer-type pairs4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Jores 2021 promoter strength: maize-protoplasts2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Jores 2021 promoter strength: tobacco-leaves2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
K562 ONT long-read RNA-seq, recovery of 6 known fusions and count of other calls (Dorney et al. 2026)6 evaluations · 152 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Karius 2019 plasma microbial cfDNA positive agreement with initial blood culture protocol1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Kedzierska et al. 2025 cell embedding scoring after UMAP projection56 evaluations · 360 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions56 evaluations · 416 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Kedzierska et al. 2025 Geneformer pretraining-objective reconstruction1 evaluation · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
KIBA drug-target affinity, DeepDTA holdout fold16 evaluations · 32 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Lancet paper virtual-tumor SNV/indel benchmark2 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Latency of a design request on one NVIDIA H20 (HyInv report)13 evaluations · 23 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
LectinOracle interaction · Interaction (GlycanML protein-glycan interaction prediction)10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Paper table does not enumerate trained checkpoint hashes; source configuration names retained.
Ligand-pocket computational pass rate under TorchScore confidence0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Lin et al. 2025 CIViC evidence-level assignment4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Lin et al. 2025 FoundationOne variants: clinically relevant vs VUS6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Lin et al. 2025 OncoKB level-of-evidence assignment6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Lipase EstA dataset stability ranking, Spearman correlation (Chu et al. 2024 Table 1)7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
LiPP Table 2: lipid pose all-atom RMSD below 2 Angstrom, Full LiPP set5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
LiPP Table 2: lipid pose all-atom RMSD below 2 Angstrom, LiPP test set5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
LiPP Table 2: lipid pose all-atom RMSD below 2 Angstrom, PoseBusters v13 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
LiPP Table 2: lipid pose all-atom RMSD below 2 Angstrom, PoseBusters v23 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
LiPP Table 3: RMSD below 2 Angstrom and PoseBusters valid, Full LiPP set5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
LiPP Table 3: RMSD below 2 Angstrom and PoseBusters valid, LiPP test set5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
LiPP Table 3: RMSD below 2 Angstrom and PoseBusters valid, PoseBusters v21 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
LIT-PCBA five-target screening (Shen et al. 2025 Table 4)7 evaluations · 84 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Livesey and Marsh 2025 clinical benchmark: pairwise AUROC win rate, ClinVar pathogenic versus gnomAD missense85 evaluations · 85 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, all 36 DMS sets97 evaluations · 194 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, direct assays only97 evaluations · 97 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, indirect assays only97 evaluations · 97 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions only97 evaluations · 97 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled97 evaluations · 97 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Local likelihood ratio at developer-recommended thresholds (Pejaver et al. 2022 Table 3)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Localization, 10-class (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Localization, binary (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
LoFreq execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1)11 evaluations · 42 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Low-mutation-burden tumours (AML, MBL, CLL), tumour-only SNVs, AUPRC (Krishnamachari et al. 2026 Supplementary Table 4)9 evaluations · 27 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 Monomeric RNA easy set, GDT-TS success rate8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 Monomeric RNA easy set, INF success rate8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 Monomeric RNA easy set, lDDT success rate8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 Monomeric RNA easy set, mean GDT-TS8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 Monomeric RNA easy set, mean INF8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 Monomeric RNA easy set, mean lDDT8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 Monomeric RNA easy set, mean TM-score10 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 Monomeric RNA easy set, TM-score success rate10 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 Monomeric RNA hard set, GDT-TS success rate7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 Monomeric RNA hard set, INF success rate8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 Monomeric RNA hard set, lDDT success rate8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 Monomeric RNA hard set, mean GDT-TS8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 Monomeric RNA hard set, mean INF7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 Monomeric RNA hard set, mean lDDT8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 Monomeric RNA hard set, mean TM-score10 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 Monomeric RNA hard set, TM-score success rate10 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 RNA complex easy set, mean DockQ4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 RNA complex easy set, mean F14 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 RNA complex easy set, mean fnat4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 RNA complex easy set, mean iRMSD4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 RNA complex easy set, mean LRMSD4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 RNA complex easy set, mean TM-score4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 RNA complex hard set, mean DockQ4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 RNA complex hard set, mean F14 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 RNA complex hard set, mean fnat4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 RNA complex hard set, mean iRMSD4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 RNA complex hard set, mean LRMSD4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 RNA complex hard set, mean TM-score4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 RNA-protein interfaces, mean per-interface DockQ4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ludaic and Elofsson 2026 RNA-RNA interfaces, mean per-interface DockQ4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
M. tuberculosis read classification, real Illumina (Hall and Coin 2024 Table 8)6 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
M. tuberculosis read classification, real Nanopore (Hall and Coin 2024 Table 6)6 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
M. tuberculosis read classification, simulated Illumina (Hall and Coin 2024 Table 7)6 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
M. tuberculosis read classification, simulated Nanopore (Hall and Coin 2024 Table 5)6 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Manual versus Talos reanalysis of 219 unresolved genomes after a mean 660 days (Kaschta et al. 2026)2 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Masked-residue perplexity, held-out UniRef panel (HyPLM report)10 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Masked-residue perplexity, recent PDB chains (HyPLM report)10 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MassSpecGym · formula (MassSpecGym De novo molecule generation)3 evaluations · 18 rows6 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
MassSpecGym · formula (MassSpecGym Molecule retrieval)5 evaluations · 20 rows4 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
MassSpecGym · formula (MassSpecGym Spectrum simulation)4 evaluations · 20 rows3 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
MassSpecGym · main (MassSpecGym De novo molecule generation)3 evaluations · 18 rows6 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
MassSpecGym · main (MassSpecGym Molecule retrieval)5 evaluations · 20 rows4 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
MassSpecGym · main (MassSpecGym Spectrum simulation)4 evaluations · 20 rows5 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
MassSpecGym de novo generation with formula (bonus), Top-1 Accuracy (MassSpecGym in the Wild Table 9)10 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MassSpecGym de novo generation with formula (bonus), Top-1 MCES (MassSpecGym in the Wild Table 9)10 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MassSpecGym de novo generation with formula (bonus), Top-1 Tanimoto (MassSpecGym in the Wild Table 9)10 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MassSpecGym de novo generation with formula (bonus), Top-10 Accuracy (MassSpecGym in the Wild Table 9)10 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MassSpecGym de novo generation with formula (bonus), Top-10 MCES (MassSpecGym in the Wild Table 9)10 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MassSpecGym de novo generation with formula (bonus), Top-10 Tanimoto (MassSpecGym in the Wild Table 9)10 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MassSpecGym formula-known retrieval (bonus), Hit rate@1 (MassSpecGym in the Wild Table 3)18 evaluations · 18 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MassSpecGym formula-known retrieval (bonus), Hit rate@20 (MassSpecGym in the Wild Table 3)18 evaluations · 18 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MassSpecGym formula-known retrieval (bonus), Hit rate@5 (MassSpecGym in the Wild Table 3)18 evaluations · 18 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MassSpecGym formula-known retrieval (bonus), MCES@1 (MassSpecGym in the Wild Table 3)18 evaluations · 18 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MassSpecGym mass-based retrieval, Hit rate@1 (MassSpecGym in the Wild Table 2)6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MassSpecGym mass-based retrieval, Hit rate@20 (MassSpecGym in the Wild Table 2)6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MassSpecGym mass-based retrieval, Hit rate@5 (MassSpecGym in the Wild Table 2)6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MassSpecGym mass-based retrieval, MCES@1 (MassSpecGym in the Wild Table 2)6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MB brain tumour somatic indels, WGS (Wang et al. 2020 Table S2)12 evaluations · 48 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MB brain tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)15 evaluations · 60 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MBNL1-associated junction usage differences across myotonic dystrophy severity groups, held-out genes (SpliceAI2 paper, Pearson)1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MCF7 ONT long-read RNA-seq, recovery of 53 known fusions and count of other calls (Dorney et al. 2026)6 evaluations · 192 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Mean Spearman over ten regression splits (HyPLM report)5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Median held-out perplexity by position class in Chr5:3,500,000-4,500,0001 evaluation · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Mega-scale dataset stability ranking, Spearman correlation (Chu et al. 2024 Table 1)7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Megascale held-out test split ddG prediction (Dieckhaus et al. 2024 Table 2)12 evaluations · 36 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Meltome human cell (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Meltome mixed (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Metal-ion binding (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Methyltransferase dataset stability ranking, Spearman correlation (Chu et al. 2024 Table 1)7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MFASS splice-disrupting variant detection, all 27,733 labelled SNVs (Znabu et al. 2026)5 evaluations · 15 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MFASS v1 (superseded)0 evaluations · 0 rowsNot yet availableSuperseded record, retained for history.
MFASS v29 evaluations · 31 rows4 source-scoped figuresChecked result tables available.
MFASS: matched GENCODE 44 canonical annotation4 evaluations · 16 rows4 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Microglia caQTL effect-size prediction (AlphaGenome paper)3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
MIMIC mRNABench probes eCLIP: eCLIP prediction12 evaluations · 12 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MIMIC mRNABench probes GO: GO prediction12 evaluations · 12 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MIMIC mRNABench probes MRL (LBKWK): MRL (LBKWK) prediction12 evaluations · 12 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MIMIC mRNABench probes MRL (Sugimoto): MRL (Sugimoto) prediction12 evaluations · 12 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MIMIC mRNABench probes Protein Localization: Protein Localization prediction12 evaluations · 12 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MIMIC mRNABench probes RNA Half Life: RNA Half Life prediction12 evaluations · 12 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MIMIC mRNABench probes RNA Localization: RNA Localization prediction12 evaluations · 12 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Minibinder computational pass rate under TorchScore confidence0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Missense variants splicing-based classification (AlphaGenome paper)2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
MIST CANOPUS retrieval Cos. similarity: MIST CANOPUS fingerprint retrieval: Cos. similarity3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MIST CANOPUS retrieval Top 1: MIST CANOPUS fingerprint retrieval: Top 16 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MIST CANOPUS retrieval Top 10: MIST CANOPUS fingerprint retrieval: Top 106 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MIST CANOPUS retrieval Top 100: MIST CANOPUS fingerprint retrieval: Top 1006 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MIST CANOPUS retrieval Top 20: MIST CANOPUS fingerprint retrieval: Top 206 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MIST CANOPUS retrieval Top 200: MIST CANOPUS fingerprint retrieval: Top 2006 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MIST CANOPUS retrieval Top 5: MIST CANOPUS fingerprint retrieval: Top 56 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MIST CANOPUS retrieval Top 50: MIST CANOPUS fingerprint retrieval: Top 506 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Mitochondrial variant pathogenicity classification (Mathur and Sachidanandam 2026 Table 2)1 evaluation · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MLH1 curated clinical splicing variants: transcriptome-normalised sensitivity at a 10% background call rate (Smith and Kitzman Table S2)8 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MPRabc K562 CRISPRi enhancer–gene evaluation6 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
mRNABench Sample designed MRL2 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
mRNABench variant probes eCLIP: eCLIP binding site prediction50 evaluations · 50 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
mRNABench variant probes GO: Gene Ontology term prediction50 evaluations · 50 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
mRNABench variant probes HL: mRNA half life50 evaluations · 50 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
mRNABench variant probes MRL-HL-Pair: Paired mean ribosome load and half life50 evaluations · 50 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
mRNABench variant probes MRL-MPRA: Mean ribosome load on an MPRA library50 evaluations · 50 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
mRNABench variant probes MRL: Mean ribosome load50 evaluations · 50 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
mRNABench variant probes Prot-Loc: Protein localisation50 evaluations · 50 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
mRNABench variant probes VEP: Variant effect prediction50 evaluations · 50 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign molecular retrieval MassSpecGym formula split: formula supplied, R@1: MassSpecGym formula split retrieval with formula supplied3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign molecular retrieval MassSpecGym formula split: formula supplied, R@20: MassSpecGym formula split retrieval with formula supplied3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign molecular retrieval MassSpecGym formula split: formula supplied, R@5: MassSpecGym formula split retrieval with formula supplied3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign molecular retrieval MassSpecGym formula split: no formula, R@1: MassSpecGym formula split retrieval with no formula6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign molecular retrieval MassSpecGym formula split: no formula, R@20: MassSpecGym formula split retrieval with no formula6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign molecular retrieval MassSpecGym formula split: no formula, R@5: MassSpecGym formula split retrieval with no formula6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign molecular retrieval MassSpecGym MCES split: formula supplied, R@1: MassSpecGym MCES split retrieval with formula supplied3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign molecular retrieval MassSpecGym MCES split: formula supplied, R@20: MassSpecGym MCES split retrieval with formula supplied3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign molecular retrieval MassSpecGym MCES split: formula supplied, R@5: MassSpecGym MCES split retrieval with formula supplied3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign molecular retrieval MassSpecGym MCES split: no formula, R@1: MassSpecGym MCES split retrieval with no formula6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign molecular retrieval MassSpecGym MCES split: no formula, R@20: MassSpecGym MCES split retrieval with no formula6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign molecular retrieval MassSpecGym MCES split: no formula, R@5: MassSpecGym MCES split retrieval with no formula6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign molecular retrieval NPLIB1: formula supplied, R@1: NPLIB1 retrieval with formula supplied3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign molecular retrieval NPLIB1: formula supplied, R@20: NPLIB1 retrieval with formula supplied3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign molecular retrieval NPLIB1: formula supplied, R@5: NPLIB1 retrieval with formula supplied3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign molecular retrieval NPLIB1: no formula, R@1: NPLIB1 retrieval with no formula6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign molecular retrieval NPLIB1: no formula, R@20: NPLIB1 retrieval with no formula6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign molecular retrieval NPLIB1: no formula, R@5: NPLIB1 retrieval with no formula6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign molecular retrieval Spectraverse: formula supplied, R@1: Spectraverse retrieval with formula supplied3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign molecular retrieval Spectraverse: formula supplied, R@20: Spectraverse retrieval with formula supplied3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign molecular retrieval Spectraverse: formula supplied, R@5: Spectraverse retrieval with formula supplied3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign molecular retrieval Spectraverse: no formula, R@1: Spectraverse retrieval with no formula6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign molecular retrieval Spectraverse: no formula, R@20: Spectraverse retrieval with no formula6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign molecular retrieval Spectraverse: no formula, R@5: Spectraverse retrieval with no formula6 evaluations · 6 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign v2 retrieval: massspecgym-formula-formula-free5 evaluations · 15 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign v2 retrieval: massspecgym-formula-formula-oracle4 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign v2 retrieval: massspecgym-mces-formula-free5 evaluations · 15 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign v2 retrieval: massspecgym-mces-formula-oracle4 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign v2 retrieval: spectraverse-formula-free5 evaluations · 15 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MSAlign v2 retrieval: spectraverse-formula-oracle4 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MST1R (RON) exon 11 saturation MPSA: transcriptome-normalised sensitivity at a 10% background call rate (Smith and Kitzman Table S2)8 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Muse execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1)11 evaluations · 42 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Mutated virus mock-community profiling against ground truth (Tisza et al. 2026 Table S9)5 evaluations · 75 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Mutect2 execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1)11 evaluations · 42 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
MYBPC3 noncanonical splice-site variants: classification against mini- or midigene splicing results (Riepe et al. Table 5)11 evaluations · 121 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NA12878 WGS CNV recall and precision, 1 bp overlap (Gabrielaite et al. Table S2)8 evaluations · 16 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Naive against effector CD4 T-cell split within donors, ARI (HyCell report)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Naive against effector CD4 T-cell split, ARI (HyCell report)1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Native sequence recovery of designed sequences (HyInv report)55 evaluations · 55 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Natural versus GenomeOcean-generated DNA classification (Natural vs artificial microbial genome sequence)3 evaluations · 9 rows3 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
NCH clinically relevant fusion ascertainment2 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NLL, held-out UniRef panel (HyPLM report)12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NLL, recent PDB chains (HyPLM report)12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Norman double perturbations: expression prediction for held-out double perturbations (Ahlmann-Eltze et al. 2025 Fig. 1a and Extended Data Fig. 2a)9 evaluations · 17 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2)15 evaluations · 88 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Novel and foldable designs per de novo backbone at matched diversity (HyInv report)3 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark Enhancer types, fine-tuning (PEFT)14 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark Enhancer types, probing8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark Enhancer, fine-tuning (PEFT)14 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark Enhancer, probing8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark H2AFZ, fine-tuning (PEFT)14 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark H2AFZ, probing8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark H3K27ac, fine-tuning (PEFT)14 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark H3K27ac, probing8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark H3K27me3, fine-tuning (PEFT)14 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark H3K27me3, probing8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark H3K36me3, fine-tuning (PEFT)14 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark H3K36me3, probing8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark H3K4me1, fine-tuning (PEFT)14 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark H3K4me1, probing8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark H3K4me2, fine-tuning (PEFT)14 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark H3K4me2, probing8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark H3K4me3, fine-tuning (PEFT)14 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark H3K4me3, probing8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark H3K9ac, fine-tuning (PEFT)14 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark H3K9ac, probing8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark H3K9me3, fine-tuning (PEFT)14 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark H3K9me3, probing8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark H4K20me1, fine-tuning (PEFT)14 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark H4K20me1, probing8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark normalised summed performance (Supplementary Table 9)23 evaluations · 23 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark Promoter all, fine-tuning (PEFT)14 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark Promoter all, probing8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark Promoter non-TATA, fine-tuning (PEFT)14 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark Promoter non-TATA, probing8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark Promoter TATA, fine-tuning (PEFT)14 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark Promoter TATA, probing8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark Splice acceptor, fine-tuning (PEFT)14 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark Splice acceptor, probing8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark Splice donor, fine-tuning (PEFT)14 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark Splice donor, probing8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark Splice site all, fine-tuning (PEFT)14 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT benchmark Splice site all, probing8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT-splice-sites-acceptors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4)11 evaluations · 44 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT-splice-sites-all splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4)11 evaluations · 44 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4)11 evaluations · 44 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
NTv3 H100 GPU-hours per training stage (Boshar et al. 2025 Table 5)3 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Nucleotide Transformer benchmark under frozen-embedding probing (Datta et al. 2026 Table 1)72 evaluations · 72 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Nucleotide Transformer benchmark, reference fine-tuned scores (Datta et al. 2026 Table 1)72 evaluations · 72 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Nucleotide Transformer IA3 fine-tuning run time (Dalla-Torre et al. 2025 Methods 'Hardware')2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
OAK overall survival, Uno C-index of a predictor fitted on other cohorts1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
OGBl-ppa PPI link prediction, Accuracy (Table 6)77 evaluations · 77 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
OGBl-ppa PPI link prediction, Hits@100 (Table 5)77 evaluations · 77 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
OMIM pathogenic vs gnomAD common regulatory variants, AUPRC (GPN-MSA Supplementary Table 4)17 evaluations · 34 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
OMIM pathogenic vs gnomAD common regulatory variants, AUPRC (GPN-Star Supplementary Table 3)8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10)17 evaluations · 85 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
OncoKB benchmark (positive set not stated), median-score threshold (Chen et al. 2020 Additional file 9)33 evaluations · 165 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
OncoVI three-class assessment: ClinVar April 2025 oncogenicity assertions1 evaluation · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
OncoVI three-class assessment: Erlangen MTB variants1 evaluation · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
OncoVI three-class assessment: Guideline SOP variants1 evaluation · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
OncoVI three-class assessment: MTB selected expert reassessment2 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ONT COLO829 tumour-only, 25x to 75x, somatic indels (Chen et al. 2025 Supplementary Table 2a)4 evaluations · 84 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ONT COLO829 tumour-only, 25x to 75x, somatic SNVs (Chen et al. 2025 Supplementary Table 2a)4 evaluations · 84 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ONT HCC1395 tumour-only, 25x to 75x, somatic indels (Chen et al. 2025 Supplementary Table 2b)3 evaluations · 63 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ONT HCC1395 tumour-only, 25x to 75x, somatic SNVs (Chen et al. 2025 Supplementary Table 2b)3 evaluations · 63 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ONT Q20 ZymoBIOMICS D6300 standard, length-filtered (PromethION): species detection at 0.001% of total reads (Portik et al. 2022 Table 4)14 evaluations · 112 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ONT R10.3 ZymoBIOMICS D6300 standard, length-filtered (GridION): species detection at 0.001% of total reads (Portik et al. 2022 Table 4)14 evaluations · 112 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
OpenSplice MPRA delta PSI prediction for 283,121 single-nucleotide substitutions in 599 exons (SpliceAI2 paper, Spearman)4 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Organism-level agreement with clinical microbiological tests (CMT), 62 BALF specimens (Hu et al. 2026)2 evaluations · 36 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Organism-level agreement with composite reference standard (CRS), 62 BALF specimens (Hu et al. 2026)2 evaluations · 36 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Organism-level agreement with routine culture, 62 BALF specimens (Hu et al. 2026)2 evaluations · 36 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
OUTRIDER expression z-score at 16 known pathogenic splicing events in muscle RNA-seq (Segarra-Casas et al. Table 2)1 evaluation · 16 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PacBio HiFi COLO829 tumour-only, 50x, somatic indels (Chen et al. 2025 Supplementary Table 7a)4 evaluations · 28 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PacBio HiFi COLO829 tumour-only, 50x, somatic SNVs (Chen et al. 2025 Supplementary Table 7a)4 evaluations · 28 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Paediatric B-ALL nanopore WTS, high-depth cohort, dominant-fusion classification (Lin et al. 2026 Table 3)4 evaluations · 16 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Paediatric B-ALL nanopore WTS, low-depth cohort, dominant-fusion classification (Lin et al. 2026 Table 6)4 evaluations · 16 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Paired scTM difference from HyInv under Boltz2 (HyInv report)10 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Paired scTM difference from HyInv under ESMFold2 (HyInv report)50 evaluations · 50 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Paired scTM difference from HyInv under Protenix2 (HyInv report)10 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Pan_dataset five-fold PPI cross-validation (protein-protein interaction prediction)3 evaluations · 15 rows5 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
Paper-specific Plinder-L95 stereochemistry assessment; Table 1 all entries · Plinder-L95 · co-folding5 evaluations · 25 rows5 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Paper-specific Plinder-L95 stereochemistry assessment; Table 1 all entries · Plinder-L95 · docking with ground-truth-centred search box1 evaluation · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Paper-specific Plinder-L95 stereochemistry assessment; Table 1 all entries · Plinder-L95 · rigid-receptor docking1 evaluation · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Parabricks DeepVariant v4.1.0-1 versus v4.3.0-1 on 8 H100 GPUs (Samarakoon et al. 2025 Table S4)2 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Patient-level detection of causative pathogens in blood against the final clinical diagnosis (Huang et al. 2026 Table 2)4 evaluations · 80 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PBMC deconvolution, pairwise ordering accuracy, mean over five lineages6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PBMC deconvolution, Pearson r of inferred against measured shares, mean over five lineages6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PBMC deconvolution, per-lineage Pearson r of inferred against measured shares2 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PCAWG ten primary tumours, tumour-only SNVs, AUPRC (Krishnamachari et al. 2026 Supplementary Table 2)9 evaluations · 90 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PDB (RNA secondary structure)10 evaluations · 40 rows4 source-scoped figuresChecked result tables available.
Scope and remaining work
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
PDBbind-2016 core set (Protein–ligand binding affinity scoring)9 evaluations · 18 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
Peak memory under 8-bit and 4-bit quantization relative to BF16 (Saadat and Fellay 2026 Figure 5)2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PepSpecBench A. thaliana OOD subset, median SA12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PepSpecBench A. thaliana OOD subset, median SAS12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PepSpecBench C. elegans OOD subset, median SA12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PepSpecBench C. elegans OOD subset, median SAS12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PepSpecBench E. coli OOD subsets (both sources aggregated), median SA12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PepSpecBench E. coli OOD subsets (both sources aggregated), median SAS12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PepSpecBench HeLa OOD subset, median SA12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PepSpecBench HeLa OOD subset, median SAS12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PepSpecBench MassIVE-KB-Mini test split, median PCC6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PepSpecBench MassIVE-KB-Mini test split, median SA6 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PepSpecBench MassIVE-KB-Mini test split, median SAS6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PepSpecBench PROSPECT-Mini test split, median PCC6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PepSpecBench PROSPECT-Mini test split, median SA6 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PepSpecBench PROSPECT-Mini test split, median SAS6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PepSpecBench Yeast OOD subset, median SA12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PepSpecBench Yeast OOD subset, median SAS12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PertEval-scFM Norman single-gene (2,000 HVGs) AUSPC across SPECTRA sparsification splits3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Perturbation-first AUROC, K562 CRISPRa (Kendiukhov 2026)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Perturbation-first AUROC, K562 CRISPRi (Kendiukhov 2026)5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Perturbation-first AUROC, RPE1 CRISPRi (Kendiukhov 2026)9 evaluations · 9 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Perturbation-first AUROC, RPE1 CRISPRi restricted to the top 2,000 HVGs (Kendiukhov 2026)1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PerturBench v4 combination prediction of held-out dual perturbations on Norman1911 evaluations · 67 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PerturBench v4 covariate transfer from mono-culture to co-culture on Frangieh2110 evaluations · 63 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PerturBench v4 covariate transfer of small-molecule effects across PBMC cell types on OP38 evaluations · 55 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PerturBench v4 covariate transfer to a held-out cell line on Srivatsan2011 evaluations · 67 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PerturBench v4 covariate transfer to held-out perturbations in held-out biological states on Jiang247 evaluations · 48 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PerturBench v4 mode-collapse diagnostics on Frangieh215 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PerturBench v4 mode-collapse diagnostics on Srivatsan205 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PerturbPFN in-prior latent recovery on held-out synthetic episodes (Table 1)1 evaluation · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PGB promoter strength maize protoplasts: A. thaliana: promoter strength prediction2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PGB promoter strength maize protoplasts: S. bicolor: promoter strength prediction2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PGB promoter strength maize protoplasts: Z. mays: promoter strength prediction2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PGB promoter strength tobacco leaves: A. thaliana: promoter strength prediction2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PGB promoter strength tobacco leaves: S. bicolor: promoter strength prediction2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PGB promoter strength tobacco leaves: Z. mays: promoter strength prediction2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PGB terminator strength maize protoplasts: A. thaliana: terminator strength prediction2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PGB terminator strength maize protoplasts: randomized GC sequences: terminator strength prediction2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PGB terminator strength maize protoplasts: Z. mays: terminator strength prediction2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PGB terminator strength tobacco leaves: A. thaliana: terminator strength prediction2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PGB terminator strength tobacco leaves: randomized GC sequences: terminator strength prediction2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PGB terminator strength tobacco leaves: Z. mays: terminator strength prediction2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Picking the top AlphaFold3 model per antibody-antigen target with a confidence score9 evaluations · 27 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PLABench CASP16 L1000 affinity9 evaluations · 54 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PLABench CASP16 L3000 affinity9 evaluations · 54 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PLABench ChEMBL35 leakage-controlled affinity9 evaluations · 63 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PLABench Davis, cold-drug split3 evaluations · 18 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PLABench Davis, cold-target split3 evaluations · 18 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PLABench Davis, warm split3 evaluations · 18 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PLABench KIBA, cold-drug split3 evaluations · 18 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PLABench KIBA, cold-target split3 evaluations · 18 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PLABench KIBA, warm split3 evaluations · 18 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
pLDDT of ESMFold2 predictions of designed sequences (HyInv report)60 evaluations · 60 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
POISK 1-in-50 screening simulation, top-1 retrieval6 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
POISK 1-in-50 screening simulation, top-10 retrieval2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
POISK binder-decoy separation in full-Fv ipSAE, Cohen's d6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
POISK binder-decoy separation in ipTM, Cohen's d6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
POISK epitope contact recovery6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
POISK pair coverage under cross-model structural consensus2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
POISK pairs left undecidable by identical ipSAE6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
POISK pairwise binder-versus-decoy accuracy at 10% coverage6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
POISK pairwise binder-versus-decoy accuracy at 100% coverage6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
POISK pairwise binder-versus-decoy accuracy at 25% coverage6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
POISK pairwise binder-versus-decoy accuracy at 50% coverage6 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
POISK pairwise binder-versus-decoy accuracy at 75% coverage6 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
POISK pairwise binder-versus-decoy accuracy under cross-model structural consensus2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Polyadenylation-QTL causality (AlphaGenome paper)2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
Positive-control virus detection by read depth (Tisza et al. 2026 Table S2)5 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
POU1F1 exon 2 saturation MPSA: transcriptome-normalised sensitivity at a 10% background call rate (Smith and Kitzman Table S2)8 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PP3/BP4 score intervals on the points scale (Bergquist et al. 2025 Table 1)7 evaluations · 63 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PP3/BP4 score intervals per evidence strength (Pejaver et al. 2022 Table 2)13 evaluations · 104 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Predicted affinity of designed ligand pockets0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Predictive sensitivity, day -3 to -1 (Wolf et al. 2026 Table 2)1 evaluation · 18 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Predictive specificity in control samples (Wolf et al. 2026 Table 3)2 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Predictive-class counts for dimeric predictions, all structures in the class (Table 2, column 'No.')3 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Predictive-class counts for dimeric predictions, heterodimeric structures in the class (Table 2, column 'Heterodimer')3 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Predictive-class counts for dimeric predictions, homodimeric structures in the class (Table 2, column 'Homodimer')3 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Predictive-class counts for dimeric predictions, structures in the class whose experimental reference is electron microscopy (Table 2, column 'EM')3 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Predictive-class counts for dimeric predictions, structures in the class whose experimental reference is NMR (Table 2, column 'NMR')3 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Predictive-class counts for dimeric predictions, structures in the class whose experimental reference is X-ray diffraction (Table 2, column 'XRD')3 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Predictive-class counts for dimeric predictions, structures in the class whose pLDDT is at least 70 (Table 2, column 'pLDDT ≥ 70')3 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Predictive-class counts for dimeric predictions, structures in the class with template quality 0 (no homologous pre-2022 structure) (Table 2, column 'TQ 0')3 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Predictive-class counts for dimeric predictions, structures in the class with template quality above 40 (Table 2, column 'TQ > 40')3 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Predictive-class counts for dimeric predictions, structures in the class with template quality between 1 and 40 (Table 2, column 'TQ 1–40')3 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Predictive-class counts for monomeric predictions, all structures in the class (Table 1, column 'No.')3 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Predictive-class counts for monomeric predictions, structures in the class whose experimental reference is electron microscopy (Table 1, column 'EM')3 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Predictive-class counts for monomeric predictions, structures in the class whose experimental reference is NMR (Table 1, column 'NMR')3 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Predictive-class counts for monomeric predictions, structures in the class whose experimental reference is X-ray diffraction (Table 1, column 'XRD')3 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Predictive-class counts for monomeric predictions, structures in the class whose pLDDT is at least 70 (Table 1, column 'pLDDT ≥ 70')3 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Predictive-class counts for monomeric predictions, structures in the class with template quality 0 (no homologous pre-2022 structure) (Table 1, column 'TQ 0')3 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Predictive-class counts for monomeric predictions, structures in the class with template quality above 40 (Table 1, column 'TQ > 40')3 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Predictive-class counts for monomeric predictions, structures in the class with template quality between 1 and 40 (Table 1, column 'TQ 1–40')3 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Pretraining GPUs and runtime for short-range models (HyenaDNA Table A.2)4 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PRIME ACE2 binding regression, Position-stratified split holding out whole mutated positions, R²21 evaluations · 21 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PRIME ACE2 binding regression, Position-stratified split holding out whole mutated positions, RMSE21 evaluations · 21 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PRIME ACE2 binding regression, Random split over RBD mutants, R²21 evaluations · 21 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PRIME ACE2 binding regression, Random split over RBD mutants, RMSE21 evaluations · 21 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PRIME RBD expression regression, Position-stratified split holding out whole mutated positions, R²21 evaluations · 21 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PRIME RBD expression regression, Position-stratified split holding out whole mutated positions, RMSE21 evaluations · 21 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PRIME RBD expression regression, Random split over RBD mutants, R²21 evaluations · 21 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PRIME RBD expression regression, Random split over RBD mutants, RMSE21 evaluations · 21 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PRO-cap prediction on held-out peaks (AlphaGenome paper)2 evaluations · 4 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
Project Score target-priority scoring v2.00 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Propensity-matched edge AUROC (Kendiukhov 2026)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Protective-antigen classification feature comparison (vaccine-antigen candidate prediction)3 evaluations · 21 rows7 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
ProteinGym AMFR official zero-shot Spearman snapshot97 evaluations · 97 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22)18 evaluations · 18 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym clinical substitutions, supervised predictors, average AUC (commit 144fe22)17 evaluations · 17 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym DMS TADBP binary classification, AUROC (GPN-MSA paper)2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym human deep mutational scanning, mean Spearman (GPN-Star Supplementary Table 3)8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym v1.3 AMFR seeded-random control1 evaluation · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym v1.3 AMFR substitution assay1 evaluation · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym v1.3 zero-shot DMS substitutions97 evaluations · 1,746 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym zero-shot (HyPLM report)17 evaluations · 17 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym zero-shot paired difference from HyPLM-Flash (HyPLM report)4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym zero-shot, activity assays (HyPLM report)7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym zero-shot, binding assays (HyPLM report)7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym zero-shot, expression assays (HyPLM report)7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym zero-shot, organismal fitness assays (HyPLM report)7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ProteinGym zero-shot, stability assays (HyPLM report)7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Pseudo-perplexity agreement between reference and efficient implementations (Saadat and Fellay 2026 Figure 1)4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
PTEN dataset stability ranking, Spearman correlation (Chu et al. 2024 Table 1)7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Public FEP benchmark, FEP+ accuracy against experiment1 evaluation · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Rank of known disease genes in 12 Kremer fibroblast RNA samples, aberrant expression (Segers et al. Table 2)4 evaluations · 48 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Rank of known disease genes in 12 Kremer fibroblast RNA samples, aberrant splicing (Segers et al. Table 2)3 evaluations · 36 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, ClinVar (Kafkas et al. 2025 Table 3)3 evaluations · 60 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, GPCards (Kafkas et al. 2025 Table 3)2 evaluations · 40 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, PAVS (Kafkas et al. 2025 Table 3)3 evaluations · 60 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Rare complex-trait SNVs versus matched controls, AUPRC (AlphaGenome Atlas)2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Rare versus common variant enrichment in the lowest 0.1% of scores, 1001 Genomes1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Re-ranking the AmpC beta-lactamase docking hit list by co-folding and docking scores (Kim, Correy, Hall et al. 2026)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Re-ranking the Dopamine D4 receptor docking hit list by co-folding and docking scores (Kim, Correy, Hall et al. 2026)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Re-ranking the Sigma-2 receptor docking hit list by co-folding and docking scores (Kim, Correy, Hall et al. 2026)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Read classification on 30 ONT pseudo-mock communities of out-of-database species (Peres da Silva et al. 2024)5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
real_test PPI held-out evaluation (protein-protein interaction prediction)3 evaluations · 18 rows6 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
Recovery of known allelic-imbalance genes and outlier calls in true-negative samples, patient muscle RNA-seq (Silverstein et al. Table S9, ANEVA-H and MAE)2 evaluations · 18 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Recovery of known expression-outlier genes and outlier calls in true-negative samples, patient RNA-seq (Silverstein et al. Table S9, OUTRIDER)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Recovery of known pathogenic splicing events and outlier calls in true-negative samples, patient RNA-seq (Silverstein et al. Table S9, splicing tools)5 evaluations · 45 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Relative abundance of each species in ZymoBIOMICS Standard II against its theoretical distribution (Song et al. 2025 Table 1)4 evaluations · 36 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Relative abundance of viridans group streptococci in culture-positive patient blood and negative controls (Song et al. 2025 Table 2)4 evaluations · 28 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Remote homology (fold) (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Repeat-assay reproducibility of relative binding free energies1 evaluation · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Replogle et al. 2022 genome-wide Perturb-seq subset, K562 CRISPRi: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2)15 evaluations · 88 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Replogle et al. 2022 genome-wide Perturb-seq subset, RPE1 CRISPRi: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2)15 evaluations · 88 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Replogle K562: expression prediction for unseen single perturbations (Ahlmann-Eltze et al. 2025 Fig. 2a and Extended Data Fig. 8a)7 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Replogle RPE1: expression prediction for unseen single perturbations (Ahlmann-Eltze et al. 2025 Fig. 2a and Extended Data Fig. 8a)7 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Respiratory virus detection against PCR, family level, read-count cut-off 0 (Carbo et al. 2022 Supplementary Table 1)15 evaluations · 165 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Respiratory virus detection against PCR, genus level, read-count cut-off 0 (Carbo et al. 2022 Supplementary Table 1)15 evaluations · 165 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Respiratory virus detection against PCR, species level, read-count cut-off 0 (Carbo et al. 2022 Supplementary Table 1)15 evaluations · 165 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Respiratory virus detection against PCR, species level, read-count cut-off 10 (Carbo et al. 2022 Supplementary Table 1)15 evaluations · 165 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Retrospective active learning on a fully measured two-gene CRISPR viability screen: top-200 gene pairs found by round 45 evaluations · 152 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Rfam12.3–14.10 (RNA secondary structure)10 evaluations · 40 rows4 source-scoped figuresChecked result tables available.
Scope and remaining work
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
RhoFold+ 2024 CASP15 natural RNA comparison R1107-rmsd: R1107: RMSD8 evaluations · 8 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
RhoFold+ 2024 CASP15 natural RNA comparison R1107-sum_z_gdt_ts_tm_score: R1107: Sum of Z-scores for GDT-TS and TM-score8 evaluations · 8 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
RhoFold+ 2024 CASP15 natural RNA comparison R1108-rmsd: R1108: RMSD8 evaluations · 8 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
RhoFold+ 2024 CASP15 natural RNA comparison R1108-sum_z_gdt_ts_tm_score: R1108: Sum of Z-scores for GDT-TS and TM-score8 evaluations · 8 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
RhoFold+ 2024 CASP15 natural RNA comparison R1116-rmsd: R1116: RMSD10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
RhoFold+ 2024 CASP15 natural RNA comparison R1116-sum_z_gdt_ts_tm_score: R1116: Sum of Z-scores for GDT-TS and TM-score10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
RhoFold+ 2024 CASP15 natural RNA comparison R1117-rmsd: R1117: RMSD10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
RhoFold+ 2024 CASP15 natural RNA comparison R1117-sum_z_gdt_ts_tm_score: R1117: Sum of Z-scores for GDT-TS and TM-score10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
RhoFold+ 2024 CASP15 natural RNA comparison R1149-rmsd: R1149: RMSD10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
RhoFold+ 2024 CASP15 natural RNA comparison R1149-sum_z_gdt_ts_tm_score: R1149: Sum of Z-scores for GDT-TS and TM-score10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
RhoFold+ 2024 CASP15 natural RNA comparison R1156-rmsd: R1156: RMSD10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
RhoFold+ 2024 CASP15 natural RNA comparison R1156-sum_z_gdt_ts_tm_score: R1156: Sum of Z-scores for GDT-TS and TM-score10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
RhoMax WT-background holdout mean3 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
RhoMax WT-background holdout split 13 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
RhoMax WT-background holdout split 23 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
RhoMax WT-background holdout split 33 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
RhoMax WT-background holdout split 43 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
RNA expression correlation across genes (AlphaGenome paper)2 evaluations · 4 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
RNA expression correlation across tracks (AlphaGenome paper)2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
RNA-seq confirmation of SpliceAI2-prioritised rare variants in panel genes, Genomics England rare-disease participants (SpliceAI2 paper)1 evaluation · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
RNA-seq track prediction at 32 bp (AlphaGenome paper)2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
RNAGym v0.1.1 fitness, signed Spearman, Aptamer16 evaluations · 16 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
RNAGym v0.1.1 fitness, signed Spearman, macro over 3 ncRNA categories16 evaluations · 16 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
RNAGym v0.1.1 fitness, signed Spearman, Ribozyme16 evaluations · 16 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
RNAGym v0.1.1 fitness, signed Spearman, tRNA16 evaluations · 16 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
RVDB 33-class viral classification by nearest-neighbour retrieval over frozen embeddings (Bůžková et al. 2026 Table 3)36 evaluations · 36 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10)5 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
RVDB viral classification: best frozen-embedding configuration against BLAST (Bůžková et al. 2026 Table 7)6 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
S669 direct and reverse ddG prediction (Pancotti et al. 2022 Table 1)21 evaluations · 231 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
S669 direct ddG prediction (Dieckhaus et al. 2024 Table 3)13 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Scaffold-Lab unconditional generation: Ci28 evaluations · 28 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Scaffold-Lab unconditional generation: Designability(↑)28 evaluations · 28 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Scaffold-Lab unconditional generation: Diversity (↑)28 evaluations · 28 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Scaffold-Lab unconditional generation: Efficiency (↓)28 evaluations · 28 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Scaffold-Lab unconditional generation: Mean Ci10 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Scaffold-Lab unconditional generation: Novelty(↓)28 evaluations · 28 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Scaffold-Lab unconditional generation: Rank10 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
scFoundation cell-type annotation comparison Segerstolpe: Segerstolpe cell-type annotation7 evaluations · 7 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
scFoundation cell-type annotation comparison Zheng68K: Zheng68K cell-type annotation7 evaluations · 7 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2)7 evaluations · 41 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
scIB batch correction (HyCell report)14 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
scIB biological conservation (HyCell report)55 evaluations · 55 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
scIB official RNA metrics export · pancreas69 evaluations · 821 rows13 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SCMBench paired RNA-ATAC integration accuracy128 evaluations · 128 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SCMBench unpaired RNA-ATAC integration accuracy113 evaluations · 113 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
scTab deep-ensemble uncertainty ROC-AUC: known-type correct vs. incorrect (Group 1 vs. Group 2)1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
scTab deep-ensemble uncertainty ROC-AUC: known-type vs. absent-type (Group 1 vs. Group 3)1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
scTab Table 1a: seeded model fits11 evaluations · 11 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
scTab Table 1b: seeded fits plus donor bootstrap5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
scTab Table 2 hardware-specific resources5 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
scTM at fixed sequence diversity on the development panel (HyInv report)2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
scTM of designed sequences under Boltz2 (HyInv report)12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
scTM of designed sequences under ESMFold2 (HyInv report)60 evaluations · 60 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
scTM of designed sequences under Protenix2 (HyInv report)12 evaluations · 12 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Secondary structure (CB513) (HyPLM report)14 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation 3UTR auPRC: 3UTR: per-nucleotide annotation (auPRC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation 3UTR MCC: 3UTR: per-nucleotide annotation (MCC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation 5UTR auPRC: 5UTR: per-nucleotide annotation (auPRC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation 5UTR MCC: 5UTR: per-nucleotide annotation (MCC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation CTCF-bound auPRC: CTCF-bound: per-nucleotide annotation (auPRC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation CTCF-bound MCC: CTCF-bound: per-nucleotide annotation (MCC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation enhancer tissue-invariant auPRC: enhancer tissue-invariant: per-nucleotide annotation (auPRC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation enhancer tissue-invariant MCC: enhancer tissue-invariant: per-nucleotide annotation (MCC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation enhancer tissue-specific auPRC: enhancer tissue-specific: per-nucleotide annotation (auPRC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation enhancer tissue-specific MCC: enhancer tissue-specific: per-nucleotide annotation (MCC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation exon auPRC: exon: per-nucleotide annotation (auPRC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation exon MCC: exon: per-nucleotide annotation (MCC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation intron auPRC: intron: per-nucleotide annotation (auPRC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation intron MCC: intron: per-nucleotide annotation (MCC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation lncRNA auPRC: lncRNA: per-nucleotide annotation (auPRC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation lncRNA MCC: lncRNA: per-nucleotide annotation (MCC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation polyA signal auPRC: polyA signal: per-nucleotide annotation (auPRC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation polyA signal MCC: polyA signal: per-nucleotide annotation (MCC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation promoter tissue-invariant auPRC: promoter tissue-invariant: per-nucleotide annotation (auPRC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation promoter tissue-invariant MCC: promoter tissue-invariant: per-nucleotide annotation (MCC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation promoter tissue-specific auPRC: promoter tissue-specific: per-nucleotide annotation (auPRC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation promoter tissue-specific MCC: promoter tissue-specific: per-nucleotide annotation (MCC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation protein coding gene auPRC: protein coding gene: per-nucleotide annotation (auPRC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation protein coding gene MCC: protein coding gene: per-nucleotide annotation (MCC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation splice acceptor auPRC: splice acceptor: per-nucleotide annotation (auPRC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation splice acceptor MCC: splice acceptor: per-nucleotide annotation (MCC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation splice donor auPRC: splice donor: per-nucleotide annotation (auPRC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SegmentNT human genome annotation splice donor MCC: splice donor: per-nucleotide annotation (MCC)21 evaluations · 21 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Self-consistency RMSD of designed sequences under ESMFold2 (HyInv report)60 evaluations · 60 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SEQC2 HCC1395 library preparation and DNA input, indel F1 (Sahraeian et al. 2022 Table S4)15 evaluations · 105 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4)17 evaluations · 119 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SEQC2 HCC1395 sequencing centre and platform, indel F1 (Sahraeian et al. 2022 Table S2)15 evaluations · 330 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)17 evaluations · 374 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SEQC2 HCC1395 tumour purity, coverage and normal contamination, indel F1 (Sahraeian et al. 2022 Table S3)15 evaluations · 720 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)17 evaluations · 816 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SEQC2 HCC1395 tumour-only, indels, AUPRC (Krishnamachari et al. 2026 Supplementary Table 1)9 evaluations · 9 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SEQC2 HCC1395 tumour-only, SNVs, AUPRC (Krishnamachari et al. 2026 Supplementary Table 1)9 evaluations · 9 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SEQC2 HCC1395 WES validation sample, somatic indels (Guille et al. 2025 Table S7)15 evaluations · 90 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SEQC2 HCC1395 WES validation sample, somatic SNVs (Guille et al. 2025 Table S7)18 evaluations · 108 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Sequence diversity of a design set (HyInv report)55 evaluations · 55 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SF3B1-associated junction usage differences in uveal melanoma, held-out genes (SpliceAI2 paper, Pearson)1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SGE held-out screens pooled, functionally abnormal versus normal SNVs, AUPRC (AlphaGenome Atlas)7 evaluations · 7 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SGE held-out screens pooled, SNVs and indels, AUPRC (AlphaGenome Atlas)5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Share of further OPA1 pathogenic substitutions and VUS called splice-altering (Alavi Table III, extended corpus)13 evaluations · 26 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Share of gnomAD variants called pathogenic at developer thresholds (Pejaver et al. 2022 Table 3)3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Share of simulated repeat variants scored below the first decile of missense variants3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Simulated long-read fusion detection, 400 fusions at three depths and three read identities (Dorney et al. 2026)6 evaluations · 250 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SJC test split (protein-small molecule binding-site prediction)4 evaluations · 16 rows4 source-scoped figuresChecked result tables available.
Scope and remaining work
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
So 2024 VarSome-vs-CanVIG-UK agreement on conflicting BRCA1 missense variants1 evaluation · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SomaticSniper execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1)11 evaluations · 42 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Species profiling on Dilthey2019 simulated long reads (Long-read taxonomic profiling)7 evaluations · 21 rows3 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
Speed-up of a design request over ProteinMPNN on one NVIDIA H20 (HyInv report)4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SPI1 binding QTL classification (AlphaGenome paper)3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
SPI1 binding QTL effect-size prediction (AlphaGenome paper)3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
Splice-altering variant classification, Barbosa et al. ClinVar intronic SNV benchmark (53,600 variants) (Fortier et al. Table 5)4 evaluations · 16 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Splice-altering variant classification, Barbosa et al. deep intronic pathogenic variants with matched common controls (484 variants) (Fortier et al. Table 4)4 evaluations · 16 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Splice-altering variant classification, CI-SpliceAI benchmark variant set (1,316 variants) (Fortier et al. Table 1)4 evaluations · 16 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Splice-altering variant classification, Extended ClinVar benchmark (58,064 variants) (Fortier et al. Table 6)4 evaluations · 16 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Splice-altering variant classification, Riepe et al. functional splice assay variants (213 variants, ABCA4 and MYBPC3) (Fortier et al. Table 2)4 evaluations · 16 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Splice-altering variant classification, SPiP benchmark variant set (99,601 variants) (Fortier et al. Table 3)4 evaluations · 16 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Splice-defect classification of OPA1 variants with thresholds tuned on the same sets (Alavi Table III, evaluation sets)13 evaluations · 78 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Splice-effect prediction against patient-RNA or exon-trapping results, all 243 scorable variants (Drost et al. Data S1)8 evaluations · 56 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Splice-effect prediction against patient-RNA or exon-trapping results, CAGI6 Splicing VUS subset (Drost et al. Data S1)8 evaluations · 56 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Splice-effect prediction against patient-RNA or exon-trapping results, in-house diagnostic cohort (Drost et al. Data S1)8 evaluations · 56 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Splice-site-region variants splicing-based classification (AlphaGenome paper)2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV)13 evaluations · 78 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Splicing-QTL causality (AlphaGenome paper)2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
SPOT-MAS five-class tissue of origin, discovery cohort 10-fold cross-validation3 evaluations · 66 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SPOT-MAS five-class tissue of origin, independent validation cohort3 evaluations · 66 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3)13 evaluations · 50 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Stability (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
SugarBase immunogenicity · Immuno (GlycanML immunogenicity prediction)10 evaluations · 10 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Paper table does not enumerate trained checkpoint hashes; source configuration names retained.
SugarBase taxonomy · Class (GlycanML taxonomy prediction)22 evaluations · 22 rows3 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Paper table does not enumerate trained checkpoint hashes; source configuration names retained.
SugarBase taxonomy · Domain (GlycanML taxonomy prediction)22 evaluations · 22 rows3 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Paper table does not enumerate trained checkpoint hashes; source configuration names retained.
SugarBase taxonomy · Family (GlycanML taxonomy prediction)22 evaluations · 22 rows3 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Paper table does not enumerate trained checkpoint hashes; source configuration names retained.
SugarBase taxonomy · Genus (GlycanML taxonomy prediction)22 evaluations · 22 rows3 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Paper table does not enumerate trained checkpoint hashes; source configuration names retained.
SugarBase taxonomy · Kingdom (GlycanML taxonomy prediction)22 evaluations · 22 rows3 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Paper table does not enumerate trained checkpoint hashes; source configuration names retained.
SugarBase taxonomy · Mean Acc (GlycanML taxonomy prediction)14 evaluations · 14 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Paper table does not enumerate trained checkpoint hashes; source configuration names retained.
SugarBase taxonomy · Order (GlycanML taxonomy prediction)22 evaluations · 22 rows3 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Paper table does not enumerate trained checkpoint hashes; source configuration names retained.
SugarBase taxonomy · Phylum (GlycanML taxonomy prediction)22 evaluations · 22 rows3 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Paper table does not enumerate trained checkpoint hashes; source configuration names retained.
SugarBase taxonomy · Species (GlycanML taxonomy prediction)22 evaluations · 22 rows3 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Paper table does not enumerate trained checkpoint hashes; source configuration names retained.
Sun et al. 2024 five-cancer detection from deconvolved plasma cfMethyl-Seq (ROC-AUC per cancer type)5 evaluations · 25 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Sun et al. 2024 liver cancer detection from deconvolved plasma WGBS (ROC-AUC)5 evaluations · 5 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Sun et al. 2026 cellular-context DE classification (cross cell line)45 evaluations · 90 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Sun et al. 2026 unseen-perturbation DE classification (within cell line)40 evaluations · 80 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Supervised distance-balanced eQTL causality (AlphaGenome paper)2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
Supervised enhancer–gene linking (AlphaGenome paper)2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
Supervised GTEx splicing-outlier prediction (AlphaGenome paper)2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
Supervised multimodal CAGI5 MPRA prediction (AlphaGenome paper)2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
Survival transfer CPTAC to TCGA, mean Uno C-index over six cancers8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Survival transfer TCGA and CPTAC, pan-cancer Uno C-index, mean of two directions8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Survival transfer TCGA to CPTAC, mean Uno C-index over six cancers8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Synthetic WES tumour-normal pair, 4,709 inserted COSMIC SNVs (López-Cade et al. 2025 Table 1)3 evaluations · 18 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Talos diagnosis recovery and workload: ACG full2 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Talos diagnosis recovery and workload: ACG singleton2 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Talos diagnosis recovery and workload: ACG trio2 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Talos diagnosis recovery and workload: RGP full2 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Talos diagnosis recovery and workload: RGP singleton2 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Talos diagnosis recovery and workload: RGP trio2 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Talos programme reanalysis yield1 evaluation · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Talos recovery of known P/LP and VUS variants in 162 trio cases (Kaschta et al. 2026)2 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Talos recovery of known P/LP and VUS variants in 45 singleton cases (Kaschta et al. 2026)1 evaluation · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Target-level detection of respiratory pathogens against routine multiplex PCR, validation set (Sanderson et al. 2026)2 evaluations · 14 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Telling cognate from shuffled nanobody-antigen pairs by ipTM3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Test perplexity on Arabidopsis thaliana chromosome 5, chromosome-wide4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Test perplexity on Arabidopsis thaliana chromosome 5, non-repeat regions4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TF ChIP-seq track prediction at 128 bp (AlphaGenome paper)3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
TF ChIP-seq track prediction at 32 bp (AlphaGenome paper)2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
TF-cell-type binding on held-out chromosomes8and9 (transcription-factor DNA binding-site prediction)6 evaluations · 12 rows2 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Independent batch review before import; preserve existing observation identities.
Thermostability (HyPLM report)13 evaluations · 13 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Three-category CNV classification, per-class agreement on deletions (Zhang et al. Table 4, DEL)5 evaluations · 15 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Three-category CNV classification, per-class agreement on duplications (Zhang et al. Table 4, DUP)5 evaluations · 15 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Tissue-specific junction usage differences across GTEx tissue pairs, held-out chromosomes (SpliceAI2 paper, Pearson)1 evaluation · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TorchCraft runtime per design at 100 residues4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TorchCraft runtime per design at 200 residues4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TorchCraft runtime per design at 300 residues4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TorchCraft runtime per design at 400 residues4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TorchCraft runtime per design at 500 residues4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Training peak GPU memory under progressive optimizations, sequence length 1000, batch size 16 (Saadat and Fellay 2026 Figure 3)4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TraitGym Complex traits per trait, AUPRC, best of zero-shot and linear probing72 evaluations · 72 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TraitGym Complex traits per trait, highest AUPRC among Borzoi tracks from one tissue9 evaluations · 9 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TraitGym Complex traits, AUPRC of a single CADD input feature3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TraitGym Complex traits, global AUPRC of a matching feature3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TraitGym Complex traits, linear-probing, AUPRC by chromosome weighted average18 evaluations · 18 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TraitGym Complex traits, zero-shot, AUPRC by chromosome weighted average57 evaluations · 57 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TraitGym fine-mapped GWAS variants, AUPRC after AVI filtering (AlphaGenome Atlas)1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TraitGym Mendelian non-coding variants, AUPRC after AVI filtering (AlphaGenome Atlas)2 evaluations · 2 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TraitGym Mendelian traits per trait, AUPRC, best of zero-shot and linear probing32 evaluations · 32 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TraitGym Mendelian traits per trait, highest AUPRC among Borzoi tracks from one tissue9 evaluations · 9 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TraitGym Mendelian traits, AUPRC of a single CADD input feature3 evaluations · 3 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TraitGym Mendelian traits, global AUPRC of a matching feature1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TraitGym Mendelian traits, linear-probing, AUPRC by chromosome weighted average18 evaluations · 18 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TraitGym Mendelian traits, zero-shot, AUPRC by chromosome weighted average63 evaluations · 63 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TREC 2020 PM Phase 1: topical relevance of retrieved MEDLINE abstracts9 evaluations · 15 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
TREC 2020 PM Phase 2: evidence-tier-weighted ranking of retrieved abstracts6 evaluations · 10 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
UCSF respiratory RNA mNGS original-testing sensitivity protocol1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
UK Biobank fine-mapped coding variants, AUPRC (GPN-Star Supplementary Table 3)8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
UK Biobank fine-mapped non-coding variants, AUPRC (GPN-Star Supplementary Table 3)8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
UniProtSMB test split (protein-small molecule binding-site prediction)4 evaluations · 16 rows4 source-scoped figuresChecked result tables available.
Scope and remaining work
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
UNITE cross-validation, cancers with all tumour fractions vs healthy (Wang et al. 2026)7 evaluations · 52 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
UNITE cross-validation, cancers with ichorCNA tumour fraction 0 to 0.03 vs healthy (Wang et al. 2026)7 evaluations · 46 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026)7 evaluations · 52 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.1 vs healthy (Wang et al. 2026)7 evaluations · 43 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
vcc2026-val-1 · 2026 validation contexts A, B and C1,048 evaluations · 1,048 rows14 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
VHH computational pass rate under TorchScore confidence and ESM2 perplexity0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
VHH expression against ESM2-150M perplexity: Pearson correlation1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
VHH expression against ESM2-150M perplexity: Spearman correlation1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
VHH expression classification by ESM2-150M perplexity: Matthews correlation coefficient1 evaluation · 1 rowNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ViroBench ALL viruses host classification, G-Split, Macro-F176 evaluations · 76 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ViroBench ALL viruses host classification, T-Split, Macro-F176 evaluations · 76 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ViroBench ALL viruses taxonomy classification, G-Split, Macro-F176 evaluations · 76 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ViroBench ALL viruses taxonomy classification, T-Split, Macro-F176 evaluations · 76 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ViroBench DNA viruses host classification, G-Split, Macro-F176 evaluations · 76 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ViroBench DNA viruses host classification, T-Split, Macro-F176 evaluations · 76 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ViroBench DNA viruses taxonomy classification, G-Split, Macro-F176 evaluations · 76 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ViroBench DNA viruses taxonomy classification, T-Split, Macro-F176 evaluations · 76 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ViroBench RNA viruses host classification, G-Split, Macro-F176 evaluations · 76 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ViroBench RNA viruses host classification, T-Split, Macro-F176 evaluations · 76 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ViroBench RNA viruses taxonomy classification, G-Split, Macro-F176 evaluations · 76 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
ViroBench RNA viruses taxonomy classification, T-Split, Macro-F176 evaluations · 76 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Virtual CRISPR Difficult Benchmark: hit prediction for complex phenotypes3 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Virtual CRISPR Simple Benchmark: yes/no prediction of a screen hit28 evaluations · 100 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Virus hits against RT-PCR: true and false positives, PPV and hit-level sensitivity (de Vries et al. 2021 Supplementary Table 4)13 evaluations · 78 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), CLS embedding, 1 − OR (mean over repeated random samplings of sequence pairs)35 evaluations · 35 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), CLS embedding, AUC (mean over repeated random samplings of sequence pairs)37 evaluations · 37 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), CLS embedding, F1 (mean over repeated random samplings of sequence pairs)37 evaluations · 37 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), CLS embedding, MCC (mean over repeated random samplings of sequence pairs)37 evaluations · 37 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), FFT embedding, 1 − OR (mean over repeated random samplings of sequence pairs)35 evaluations · 35 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), FFT embedding, AUC (mean over repeated random samplings of sequence pairs)37 evaluations · 37 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), FFT embedding, F1 (mean over repeated random samplings of sequence pairs)37 evaluations · 37 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), FFT embedding, MCC (mean over repeated random samplings of sequence pairs)37 evaluations · 37 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, AUC (mean over assays)35 evaluations · 35 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, AUC (median over assays)35 evaluations · 35 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays)35 evaluations · 35 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (median over assays)35 evaluations · 35 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, SR (mean over assays)35 evaluations · 35 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, SR (median over assays)35 evaluations · 35 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, AUC (mean over assays)22 evaluations · 22 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, AUC (median over assays)22 evaluations · 22 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, MCC (mean over assays)22 evaluations · 22 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, MCC (median over assays)22 evaluations · 22 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, SR (mean over assays)22 evaluations · 22 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, SR (median over assays)22 evaluations · 22 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), CLS embedding, 1 − OR (mean over repeated random samplings of sequence pairs)35 evaluations · 35 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), CLS embedding, AUC (mean over repeated random samplings of sequence pairs)37 evaluations · 37 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), CLS embedding, F1 (mean over repeated random samplings of sequence pairs)37 evaluations · 37 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), CLS embedding, MCC (mean over repeated random samplings of sequence pairs)37 evaluations · 37 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, 1 − OR (mean over repeated random samplings of sequence pairs)35 evaluations · 35 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, AUC (mean over repeated random samplings of sequence pairs)37 evaluations · 37 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs)37 evaluations · 37 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, MCC (mean over repeated random samplings of sequence pairs)37 evaluations · 37 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot secondary structure, TS test set (70 PDB structures), attention, F1 score (mean over structures)32 evaluations · 32 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot secondary structure, TS test set (70 PDB structures), attention, F1 score (median over structures)32 evaluations · 32 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot secondary structure, TS test set (70 PDB structures), attention, MCC (mean over structures)32 evaluations · 32 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot secondary structure, TS test set (70 PDB structures), attention, MCC (median over structures)32 evaluations · 32 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot secondary structure, TS-Hard test set (15 PDB structures), attention, F1 score (mean over structures)32 evaluations · 32 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot secondary structure, TS-Hard test set (15 PDB structures), attention, F1 score (median over structures)32 evaluations · 32 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot secondary structure, TS-Hard test set (15 PDB structures), attention, MCC (mean over structures)32 evaluations · 32 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Wang et al. 2026 zero-shot secondary structure, TS-Hard test set (15 PDB structures), attention, MCC (median over structures)32 evaluations · 32 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
WES FASTQ-to-VCF runtime and cost on GCP, Sentieon versus Parabricks (Franzoso et al. 2025 Table S2)2 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
WGS FASTQ-to-VCF runtime and cost on GCP, Sentieon versus Parabricks (Franzoso et al. 2025 Table S2)2 evaluations · 18 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
WGS germline pipeline wall-clock, DeepVariant calling stage (Samarakoon et al. 2025 Table S3b.2)4 evaluations · 40 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
WGS germline pipeline wall-clock, HaplotypeCaller or DRAGEN GSVC calling stage (Samarakoon et al. 2025 Table S3b.1)5 evaluations · 50 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
WGS germline pipeline wall-clock, read mapping stage (Samarakoon et al. 2025 Table S3a)5 evaluations · 50 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
WGS germline pipeline wall-clock, total of read mapping and HaplotypeCaller or DRAGEN GSVC (Samarakoon et al. 2025 Table S3c)5 evaluations · 49 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
WT1 exon 9 saturation MPSA: transcriptome-normalised sensitivity at a 10% background call rate (Smith and Kitzman Table S2)8 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Xu and Feng 2026: GI cancer vs non-cancer on GSE149438, three train-validation-test split-runs, DMR-informed CpG features5 evaluations · 15 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ye et al. 2026 GRN reconstruction, TFs+1000, cell-type-specific ChIP-seq reference147 evaluations · 294 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ye et al. 2026 GRN reconstruction, TFs+1000, non-specific ChIP-seq reference147 evaluations · 294 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ye et al. 2026 GRN reconstruction, TFs+1000, OmniPath reference147 evaluations · 294 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ye et al. 2026 GRN reconstruction, TFs+1000, STRING reference147 evaluations · 294 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ye et al. 2026 GRN reconstruction, TFs+500, cell-type-specific ChIP-seq reference147 evaluations · 294 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ye et al. 2026 GRN reconstruction, TFs+500, non-specific ChIP-seq reference147 evaluations · 294 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ye et al. 2026 GRN reconstruction, TFs+500, OmniPath reference147 evaluations · 294 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Ye et al. 2026 GRN reconstruction, TFs+500, STRING reference147 evaluations · 294 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Yoruba LCL dsQTL classification (AlphaGenome paper)3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
Yoruba LCL dsQTL effect-size prediction (AlphaGenome paper)3 evaluations · 3 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
Zeng et al. 2026 independent PE validation dataset: cancer vs healthy10 evaluations · 19 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zeng et al. 2026 primary PE dataset: cancer vs healthy, nested cross-validation10 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zeng et al. 2026 primary SE dataset: cancer vs healthy, nested cross-validation3 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zeng et al. 2026 SE 10% hold-out set: cancer vs healthy3 evaluations · 6 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot BRCA1 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)15 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot BRCA1 coding SNVs classification (Evo 2 paper, Supplementary Data 1)16 evaluations · 32 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot BRCA1 intronic SNVs classification (Evo 2 paper, Supplementary Data 1)15 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot BRCA1 loss-of-function classification, all SNVs (evo2-cloud-operations W1)8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot BRCA1 loss-of-function classification, coding SNVs (missense, nonsense, synonymous) (evo2-cloud-operations W1)8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot BRCA1 loss-of-function classification, missense SNVs (evo2-cloud-operations W1)4 evaluations · 4 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot BRCA1 loss-of-function classification, noncoding SNVs (all other consequences) (evo2-cloud-operations W1)8 evaluations · 8 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot BRCA1 noncoding SNVs classification (Evo 2 paper, Supplementary Data 1)15 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot BRCA1 splice region SNVs classification (Evo 2 paper, Supplementary Data 1)15 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot BRCA2 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)14 evaluations · 28 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot BRCA2 coding SNVs classification (Evo 2 paper, Supplementary Data 1)15 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot BRCA2 noncoding SNVs classification (Evo 2 paper, Supplementary Data 1)15 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot CAGI5 MPRA activity-effect prediction (borzoi-ensemble-matched comparison) (AlphaGenome paper)2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
Zero-shot CAGI5 MPRA activity-effect prediction (chrombpnet-matched comparison) (AlphaGenome paper)2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
Zero-shot ClinVar 'Both' (coding and noncoding) indels classification (Evo 2 paper, Supplementary Data 1)10 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar 'Both' (coding and noncoding) microsatellite variants classification (Evo 2 paper, Supplementary Data 1)10 evaluations · 20 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)12 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar coding indels classification (Evo 2 paper, Supplementary Data 1)15 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar coding microsatellite variants classification (Evo 2 paper, Supplementary Data 1)15 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar coding non-SNVs classification (Evo 2 paper, Supplementary Data 1)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Zero-shot ClinVar coding non-SNVs, far from splice site classification (Evo 2 paper, Supplementary Data 1)15 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar coding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1)15 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar coding non-SNVs, moderately conserved classification (Evo 2 paper, Supplementary Data 1)15 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar coding non-SNVs, not conserved classification (Evo 2 paper, Supplementary Data 1)15 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar coding non-SNVs, poorly conserved classification (Evo 2 paper, Supplementary Data 1)15 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar coding SNVs classification (Evo 2 paper, Supplementary Data 1)18 evaluations · 36 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar coding SNVs, far from splice site classification (Evo 2 paper, Supplementary Data 1)18 evaluations · 36 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar coding SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1)18 evaluations · 36 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar coding SNVs, moderately conserved classification (Evo 2 paper, Supplementary Data 1)18 evaluations · 36 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar coding SNVs, near splice site classification (Evo 2 paper, Supplementary Data 1)18 evaluations · 36 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar coding SNVs, not conserved classification (Evo 2 paper, Supplementary Data 1)18 evaluations · 36 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar coding SNVs, poorly conserved classification (Evo 2 paper, Supplementary Data 1)18 evaluations · 36 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) non-SNVs classification (Evo 2 paper, Supplementary Data 1)11 evaluations · 22 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1)13 evaluations · 26 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar noncoding indels classification (Evo 2 paper, Supplementary Data 1)12 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar noncoding microsatellite variants classification (Evo 2 paper, Supplementary Data 1)12 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar noncoding non-SNVs classification (Evo 2 paper, Supplementary Data 1)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Zero-shot ClinVar noncoding non-SNVs, far from splice site classification (Evo 2 paper, Supplementary Data 1)12 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1)12 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar noncoding non-SNVs, intergenic classification (Evo 2 paper, Supplementary Data 1)12 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar noncoding non-SNVs, moderately conserved classification (Evo 2 paper, Supplementary Data 1)12 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar noncoding non-SNVs, near splice site classification (Evo 2 paper, Supplementary Data 1)12 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar noncoding non-SNVs, not conserved classification (Evo 2 paper, Supplementary Data 1)12 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar noncoding non-SNVs, poorly conserved classification (Evo 2 paper, Supplementary Data 1)12 evaluations · 24 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar noncoding SNVs classification (Evo 2 paper, Supplementary Data 1)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
Zero-shot ClinVar noncoding SNVs, far from splice site classification (Evo 2 paper, Supplementary Data 1)14 evaluations · 28 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar noncoding SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1)15 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar noncoding SNVs, intergenic classification (Evo 2 paper, Supplementary Data 1)14 evaluations · 28 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar noncoding SNVs, moderately conserved classification (Evo 2 paper, Supplementary Data 1)15 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar noncoding SNVs, near splice site classification (Evo 2 paper, Supplementary Data 1)14 evaluations · 28 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar noncoding SNVs, not conserved classification (Evo 2 paper, Supplementary Data 1)15 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot ClinVar noncoding SNVs, poorly conserved classification (Evo 2 paper, Supplementary Data 1)15 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot distance-balanced eQTL causality (AlphaGenome paper)2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
Zero-shot enhancer–gene linking (AlphaGenome paper)2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
Zero-shot GTEx splicing-outlier prediction (AlphaGenome paper)2 evaluations · 2 rows1 source-scoped figuresChecked result tables available.
Scope and remaining work
  • Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
  • Subsequent studies use different datasets and are not pooled with this paper.
Zero-shot SpliceVarDB 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)15 evaluations · 30 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot SpliceVarDB exonic SNVs classification (Evo 2 paper, Supplementary Data 1)16 evaluations · 32 rowsNot yet availableResults available; comparison group not yet validated.
Scope and remaining work
  • Only reviewed, source-scoped comparison groups are charted. Individual observations remain in the results table.
Zero-shot SpliceVarDB intronic SNVs classification (Evo 2 paper, Supplementary Data 1)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.

Evaluators

9 pages · 0 with results · 0 with charts.

PageEvaluations and metric rowsChartsCollection status
AMBER0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • Do not rank AMBER as a predictor; AMBER is the scoring implementation.
  • Gold-standard 596 is a reference ceiling, not a competing method.
  • These are recovered-genome counts, not bin-level precision or seed-averaged means; no uncertainty in Table 1.
BenchBench-Cloning agreement judge (Claude Mythos 5.1)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BenchBench-Cloning cloning simulator0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BenchBench-Cloning construct-design deterministic graders0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
BenchBench-Cloning rubric judge (GPT-6 Astra)0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.
OPAL0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • OPAL is an evaluator rather than a single dataset. Numerical comparisons require selected community dataset, taxonomic rank and profiling output version. No complete main-text score matrix; source data remains pending.
PoseBusters0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • Main tables define benchmark/validity tests, not a complete method score matrix. Individual docking output data at Zenodo 8278563 identified for next extraction. RMSD-only and RMSD-plus-validity must stay distinct.
scPertEval0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • Supplementary Figure 1 reuses a separate Wei et al. benchmark; its origin must be retained rather than attributed as newly run scPertEval model results.
  • No universal default metric/normalization or scientific model winner is implied by the evaluator.
TorchScore0 evaluations · 0 rowsNot yet availablePublished results still to collect.
Scope and remaining work
  • No evaluations linked in this release; this is a catalogue gap, not a claim that no published experiments exist.