rewirebio.iobenchmarks
Configuration

HyPLM-Flash, BF16 evaluation (HyPLM report)

Runs the released HyPLM-Flash weights in BF16 arithmetic to produce embeddings, probe features and masked-language-model scores.

40 evaluations · 40 results

Overview

An explanatory profile has not yet been reviewed for this record.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

Model Capabilities & Hardware Requirements

Deployment facts recorded for HyPLM-Flash, BF16 evaluation (HyPLM report). Fields the record does not carry are marked not recorded.

ParametersNot recorded
Minimum VRAMNot recorded
Inference LatencyNot recorded
Context WindowNot recorded
AccessNot recorded
LicenseNot recorded

Evaluated Checkpoint: Released weights; report dated 2026-10-12

Evaluations and results

40 evaluations · 40 results. Different protocols are not a single leaderboard.

Sorted by Accuracy (Binary localisation accuracy on DeepLoc 1.0 via PEER) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configurationProtocol and datasetAccuracy (Binary localisation accuracy on DeepLoc 1.0 via PEER)Accuracy (Fold-level classification accuracy on the TAPE remote-homology (SCOP) test set)Accuracy (Human protein-protein interaction classification accuracy on PEER HumanPPI, with pair features [a, b, a*b, |a-b|])Accuracy (Metal-ion binding classification accuracy on the split packaged by SaProt)Accuracy (Ten-class subcellular localisation accuracy on DeepLoc 1.0 via PEER)Accuracy (Three-state (Q3) per-residue secondary-structure accuracy on the CB513 test set)F1 max (Protein-centric Fmax over Enzyme Commission numbers on the DeepFRI EC split)F1 max (Protein-centric Fmax over Enzyme Commission numbers on the SaProt EC split)F1 max (Protein-centric Fmax over Gene Ontology biological-process terms on the DeepFRI GO split as packaged by SaProt)F1 max (Protein-centric Fmax over Gene Ontology cellular-component terms on the DeepFRI GO split as packaged by SaProt)F1 max (Protein-centric Fmax over Gene Ontology molecular-function terms on the DeepFRI GO split as packaged by SaProt)Log loss (Mean negative log-likelihood of masked residues in nats on the report's held-out UniRef panel, identical masks and crops for every model)Log loss (Mean negative log-likelihood of masked residues in nats on the report's recent-PDB panel, identical masks and crops for every model)Macro F1 (Macro-averaged F1 of Enzyme Commission classification on DGEB, with the layer and regularisation chosen by 5-fold cross-validation on the training split because this task has no validation split)Mean average precision at 5 (Zero-shot retrieval mean average precision at 5 on DGEB Arch, ranked by cosine similarity between mean-pooled representations)Perplexity (Masked-residue perplexity on the held-out UniRef panel: the exponential of the mean negative log-likelihood of masked residues under the model itself, with identical masks and crops for every model)Perplexity (Masked-residue perplexity on the recent PDB chains: the exponential of the mean negative log-likelihood of masked residues under the model itself, with identical masks and crops for every model)Precision at l 5 (Long-range contact precision of the top L/5 predictions (sequence separation at least 24) on 82 CASP14 evaluation domains)Precision at l 5 (Long-range contact precision of the top L/5 predictions (sequence separation at least 24) on 95 CASP15 evaluation domains)Precision at l 5 (Long-range contact precision of the top L/5 predictions (sequence separation at least 24) on the ProteinNet CASP12 test set of 40 proteins)Spearman (Spearman correlation averaged over the 217 substitution assays of ProteinGym v1.3 with the benchmark's official aggregation, from masked-marginal zero-shot scores; per-assay values rounded to three decimals before aggregation)Spearman (Spearman correlation averaged over the ProteinGym v1.3 substitution assays of selection type 'Activity', from masked-marginal zero-shot scores; only the authors' own runs (dagger rows of Table 5) are recorded)Spearman (Spearman correlation averaged over the ProteinGym v1.3 substitution assays of selection type 'Binding', from masked-marginal zero-shot scores; only the authors' own runs (dagger rows of Table 5) are recorded)Spearman (Spearman correlation averaged over the ProteinGym v1.3 substitution assays of selection type 'Expression', from masked-marginal zero-shot scores; only the authors' own runs (dagger rows of Table 5) are recorded)Spearman (Spearman correlation averaged over the ProteinGym v1.3 substitution assays of selection type 'Organismal fitness', from masked-marginal zero-shot scores; only the authors' own runs (dagger rows of Table 5) are recorded)Spearman (Spearman correlation averaged over the ProteinGym v1.3 substitution assays of selection type 'Stability', from masked-marginal zero-shot scores; only the authors' own runs (dagger rows of Table 5) are recorded)Spearman (Spearman correlation on the FLIP AAV low-vs-high split)Spearman (Spearman correlation on the FLIP AAV two-vs-many split)Spearman (Spearman correlation on the FLIP GB1 low-vs-high split)Spearman (Spearman correlation on the FLIP GB1 three-vs-rest split)Spearman (Spearman correlation on the FLIP GB1 two-vs-rest split)Spearman (Spearman correlation on the FLIP Meltome human-cell split)Spearman (Spearman correlation on the FLIP Meltome mixed split)Spearman (Spearman correlation on the FLIP2 amylase one-to-many split)Spearman (Spearman correlation on the FLIP2 amylase split partitioned by mutation count)Spearman (Spearman correlation on the FLIP2 cross-protein hydrolase split, training on other hydrolases and testing on P06241)Spearman (Spearman correlation on the Meltome human-cell split as packaged by SaProt, which the report lists separately from its own FLIP Meltome human-cell row)Spearman (Spearman correlation on the TAPE fluorescence regression split)Spearman (Spearman correlation on the TAPE stability regression split)Spearman (Unweighted mean of the test Spearman correlations on the ten regression splits Appendix A uses for summary statistics, excluding GB1 two-vs-rest, GB1 three-vs-rest and the FLIP2 hydrolase split)
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationLocalization, binary (HyPLM report), DeepLoc binary localisation via PEER (HyPLM report)0.906Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationAAV low-vs-high (HyPLM report), FLIP AAV, low-vs-high split (FLIP split)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.296Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationAAV two-vs-many (HyPLM report), FLIP AAV, 2-vs-rest split (FLIP split)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.65Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationAmylase by mutation count (HyPLM report), Amylase by mutation count (FLIP2, HyPLM report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.553Not reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationAmylase one-to-many (HyPLM report), Amylase one-to-many (FLIP2, HyPLM report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.696Not reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationArch retrieval (DGEB) (HyPLM report), DGEB Arch retrieval (HyPLM report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.086Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationContacts, CASP14 (HyPLM report), CASP14 evaluation domains (82, HyPLM report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.556Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationContacts, CASP15 (HyPLM report), CASP15 evaluation domains (95, HyPLM report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.574Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationContacts, ProteinNet (HyPLM report), ProteinNet CASP12Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.65Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationEC classification (DGEB) (HyPLM report), DGEB EC classification (HyPLM report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.687Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationEC, DeepFRI split (HyPLM report), EC annotation, DeepFRI split (HyPLM report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reported0.874Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationEC, SaProt split (HyPLM report), EC annotation, SaProt split (HyPLM report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.885Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationFluorescence (HyPLM report), Fluorescence (TAPE)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.669Not reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationGB1 low-vs-high (HyPLM report), FLIP GB1, low-vs-high split (FLIP split)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.469Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationGB1 three-vs-rest (HyPLM report), FLIP GB1, 3-vs-rest split (FLIP split)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.808Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationGB1 two-vs-rest (HyPLM report), FLIP GB1, 2-vs-rest split (FLIP split)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.628Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationGO-BP (HyPLM report), GO biological process, DeepFRI split via SaProt (HyPLM report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.492Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationGO-CC (HyPLM report), GO cellular component, DeepFRI split via SaProt (HyPLM report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.538Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationGO-MF (HyPLM report), GO molecular function, DeepFRI split via SaProt (HyPLM report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.661Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationHumanPPI (HyPLM report), HumanPPI via PEER (HyPLM report)Not reportedNot reported0.817Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationHydrolase to P06241 (HyPLM report), Hydrolase to P06241 (FLIP2 cross-protein, HyPLM report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported−0.192Not reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationLocalization, 10-class (HyPLM report), DeepLoc ten-class localisation via PEER (HyPLM report)Not reportedNot reportedNot reportedNot reported0.794Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationMeltome human cell (HyPLM report), FLIP Thermostability, Human-Cell split (FLIP split)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.684Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationMeltome mixed (HyPLM report), FLIP Thermostability, Mixed split (FLIP split)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.672Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationMetal-ion binding (HyPLM report), Metal-ion binding, SaProt packaging (HyPLM report)Not reportedNot reportedNot reported0.695Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationNLL, held-out UniRef panel (HyPLM report), Held-out UniRef panel (479 proteins, HyPLM report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported1.7Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationNLL, recent PDB chains (HyPLM report), Recent PDB chains (887, HyPLM report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported1.15Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationMasked-residue perplexity, held-out UniRef panel (HyPLM report), Held-out UniRef panel (479 proteins, HyPLM report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported5.46Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationMasked-residue perplexity, recent PDB chains (HyPLM report), Recent PDB chains (887, HyPLM report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported3.15Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationProteinGym zero-shot, activity assays (HyPLM report), ProteinGym DMS substitution assays at commit 144fe22 (217 assays)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.419Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationProteinGym zero-shot, binding assays (HyPLM report), ProteinGym DMS substitution assays at commit 144fe22 (217 assays)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.277Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationProteinGym zero-shot, expression assays (HyPLM report), ProteinGym DMS substitution assays at commit 144fe22 (217 assays)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.429Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationProteinGym zero-shot, organismal fitness assays (HyPLM report), ProteinGym DMS substitution assays at commit 144fe22 (217 assays)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.406Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationProteinGym zero-shot, stability assays (HyPLM report), ProteinGym DMS substitution assays at commit 144fe22 (217 assays)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.514Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationProteinGym zero-shot (HyPLM report), ProteinGym DMS substitution assays at commit 144fe22 (217 assays)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.409Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationMean Spearman over ten regression splits (HyPLM report), Ten regression splits for summary statistics (HyPLM report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.606
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationRemote homology (fold) (HyPLM report), Fold classification (TAPE)Not reported0.322Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationSecondary structure (CB513) (HyPLM report), Secondary structure prediction (TAPE)Not reportedNot reportedNot reportedNot reportedNot reported0.882Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationStability (HyPLM report), Stability (TAPE, HyPLM report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.687Not reported
HyPLM-Flash, BF16 evaluation (HyPLM report)EvaluationThermostability (HyPLM report), Thermostability, Meltome human cell via SaProt (HyPLM report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.684Not reportedNot reportedNot reported
All 40 result rows with coverage, uncertainty and sources
Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Configuration: HyPLM-Flash, BF16 evaluation (HyPLM report)Protocol: AAV low-vs-high (HyPLM report)
Dataset subset: FLIP AAV, low-vs-high split (FLIP split)
0.296 Spearman (Spearman correlation on the FLIP AAV low-vs-high split)
unitless · higher

Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyPLM-Flash on aav-low-vs-high (HyPLM report)

hyplm-flash-20261106-protocol-aav-low-vs-high

Aggregation: Not reported

HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 6, row 'AAV low-vs-high', column 'HyPLM-Flash' (page 12 of 13)
Configuration: HyPLM-Flash, BF16 evaluation (HyPLM report)Protocol: AAV two-vs-many (HyPLM report)
Dataset subset: FLIP AAV, 2-vs-rest split (FLIP split)
0.65 Spearman (Spearman correlation on the FLIP AAV two-vs-many split)
unitless · higher

Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyPLM-Flash on aav-two-vs-many (HyPLM report)

hyplm-flash-20261106-protocol-aav-two-vs-many

Aggregation: Not reported

HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 6, row 'AAV two-vs-many', column 'HyPLM-Flash' (page 12 of 13)
Configuration: HyPLM-Flash, BF16 evaluation (HyPLM report)Protocol: Amylase by mutation count (HyPLM report)
Dataset: Amylase by mutation count (FLIP2, HyPLM report)
0.553 Spearman (Spearman correlation on the FLIP2 amylase split partitioned by mutation count)
unitless · higher

Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyPLM-Flash on amylase-by-mutation-count (HyPLM report)

hyplm-flash-20261106-protocol-amylase-by-mutation-count

Aggregation: Not reported

HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 6, row 'Amylase by mutation count', column 'HyPLM-Flash' (page 12 of 13)
Configuration: HyPLM-Flash, BF16 evaluation (HyPLM report)Protocol: Amylase one-to-many (HyPLM report)
Dataset: Amylase one-to-many (FLIP2, HyPLM report)
0.696 Spearman (Spearman correlation on the FLIP2 amylase one-to-many split)
unitless · higher

Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyPLM-Flash on amylase-one-to-many (HyPLM report)

hyplm-flash-20261106-protocol-amylase-one-to-many

Aggregation: Not reported

HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 6, row 'Amylase one-to-many', column 'HyPLM-Flash' (page 12 of 13)
Configuration: HyPLM-Flash, BF16 evaluation (HyPLM report)Protocol: Arch retrieval (DGEB) (HyPLM report)
Dataset: DGEB Arch retrieval (HyPLM report)
0.086 Mean average precision at 5 (Zero-shot retrieval mean average precision at 5 on DGEB Arch, ranked by cosine similarity between mean-pooled representations)
fraction · higher

Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyPLM-Flash on arch-retrieval-dgeb (HyPLM report)

hyplm-flash-20261106-protocol-arch-retrieval-dgeb

Aggregation: Not reported

HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 6, row 'Arch retrieval (DGEB)', column 'HyPLM-Flash' (page 12 of 13)
Configuration: HyPLM-Flash, BF16 evaluation (HyPLM report)Protocol: Contacts, CASP14 (HyPLM report)
Dataset: CASP14 evaluation domains (82, HyPLM report)
0.556 Precision at l 5 (Long-range contact precision of the top L/5 predictions (sequence separation at least 24) on 82 CASP14 evaluation domains)
fraction · higher

Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyPLM-Flash on contacts-casp14 (HyPLM report)

hyplm-flash-20261106-protocol-contacts-casp14

Aggregation: Not reported

HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 6, row 'Contacts, CASP14', column 'HyPLM-Flash' (page 12 of 13)
Configuration: HyPLM-Flash, BF16 evaluation (HyPLM report)Protocol: Contacts, CASP15 (HyPLM report)
Dataset: CASP15 evaluation domains (95, HyPLM report)
0.574 Precision at l 5 (Long-range contact precision of the top L/5 predictions (sequence separation at least 24) on 95 CASP15 evaluation domains)
fraction · higher

Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyPLM-Flash on contacts-casp15 (HyPLM report)

hyplm-flash-20261106-protocol-contacts-casp15

Aggregation: Not reported

HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 6, row 'Contacts, CASP15', column 'HyPLM-Flash' (page 12 of 13)
Configuration: HyPLM-Flash, BF16 evaluation (HyPLM report)Protocol: Contacts, ProteinNet (HyPLM report)
Dataset: ProteinNet CASP12
0.65 Precision at l 5 (Long-range contact precision of the top L/5 predictions (sequence separation at least 24) on the ProteinNet CASP12 test set of 40 proteins)
fraction · higher

Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyPLM-Flash on contacts-proteinnet (HyPLM report)

hyplm-flash-20261106-protocol-contacts-proteinnet

Aggregation: Not reported

HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 6, row 'Contacts, ProteinNet', column 'HyPLM-Flash' (page 12 of 13)
Configuration: HyPLM-Flash, BF16 evaluation (HyPLM report)Protocol: EC classification (DGEB) (HyPLM report)
Dataset: DGEB EC classification (HyPLM report)
0.687 Macro F1 (Macro-averaged F1 of Enzyme Commission classification on DGEB, with the layer and regularisation chosen by 5-fold cross-validation on the training split because this task has no validation split)
fraction · higher

Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyPLM-Flash on ec-classification-dgeb (HyPLM report)

hyplm-flash-20261106-protocol-ec-classification-dgeb

Aggregation: Not reported

HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 6, row 'EC classification (DGEB)', column 'HyPLM-Flash' (page 12 of 13)
Configuration: HyPLM-Flash, BF16 evaluation (HyPLM report)Protocol: EC, DeepFRI split (HyPLM report)
Dataset: EC annotation, DeepFRI split (HyPLM report)
0.874 F1 max (Protein-centric Fmax over Enzyme Commission numbers on the DeepFRI EC split)
fraction · higher

Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyPLM-Flash on ec-deepfri-split (HyPLM report)

hyplm-flash-20261106-protocol-ec-deepfri-split

Aggregation: Not reported

HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 6, row 'EC, DeepFRI split', column 'HyPLM-Flash' (page 12 of 13)
Configuration: HyPLM-Flash, BF16 evaluation (HyPLM report)Protocol: EC, SaProt split (HyPLM report)
Dataset: EC annotation, SaProt split (HyPLM report)
0.885 F1 max (Protein-centric Fmax over Enzyme Commission numbers on the SaProt EC split)
fraction · higher

Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyPLM-Flash on ec-saprot-split (HyPLM report)

hyplm-flash-20261106-protocol-ec-saprot-split

Aggregation: Not reported

HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 6, row 'EC, SaProt split', column 'HyPLM-Flash' (page 12 of 13)
Configuration: HyPLM-Flash, BF16 evaluation (HyPLM report)Protocol: Fluorescence (HyPLM report)
Dataset: Fluorescence (TAPE)
0.669 Spearman (Spearman correlation on the TAPE fluorescence regression split)
unitless · higher

Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyPLM-Flash on fluorescence (HyPLM report)

hyplm-flash-20261106-protocol-fluorescence

Aggregation: Not reported

HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 6, row 'Fluorescence', column 'HyPLM-Flash' (page 12 of 13)
Configuration: HyPLM-Flash, BF16 evaluation (HyPLM report)Protocol: GB1 low-vs-high (HyPLM report)
Dataset subset: FLIP GB1, low-vs-high split (FLIP split)
0.469 Spearman (Spearman correlation on the FLIP GB1 low-vs-high split)
unitless · higher

Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyPLM-Flash on gb1-low-vs-high (HyPLM report)

hyplm-flash-20261106-protocol-gb1-low-vs-high

Aggregation: Not reported

HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 6, row 'GB1 low-vs-high', column 'HyPLM-Flash' (page 12 of 13)
Configuration: HyPLM-Flash, BF16 evaluation (HyPLM report)Protocol: GB1 three-vs-rest (HyPLM report)
Dataset subset: FLIP GB1, 3-vs-rest split (FLIP split)
0.808 Spearman (Spearman correlation on the FLIP GB1 three-vs-rest split)
unitless · higher

Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyPLM-Flash on gb1-three-vs-rest (HyPLM report)

hyplm-flash-20261106-protocol-gb1-three-vs-rest

Aggregation: Not reported

HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 6, row 'GB1 three-vs-rest', column 'HyPLM-Flash' (page 12 of 13)
Configuration: HyPLM-Flash, BF16 evaluation (HyPLM report)Protocol: GB1 two-vs-rest (HyPLM report)
Dataset subset: FLIP GB1, 2-vs-rest split (FLIP split)
0.628 Spearman (Spearman correlation on the FLIP GB1 two-vs-rest split)
unitless · higher

Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyPLM-Flash on gb1-two-vs-rest (HyPLM report)

hyplm-flash-20261106-protocol-gb1-two-vs-rest

Aggregation: Not reported

HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 6, row 'GB1 two-vs-rest', column 'HyPLM-Flash' (page 12 of 13)
Configuration: HyPLM-Flash, BF16 evaluation (HyPLM report)Protocol: GO-BP (HyPLM report)
Dataset: GO biological process, DeepFRI split via SaProt (HyPLM report)
0.492 F1 max (Protein-centric Fmax over Gene Ontology biological-process terms on the DeepFRI GO split as packaged by SaProt)
fraction · higher

Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyPLM-Flash on go-bp (HyPLM report)

hyplm-flash-20261106-protocol-go-bp

Aggregation: Not reported

HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 6, row 'GO-BP', column 'HyPLM-Flash' (page 12 of 13)
Configuration: HyPLM-Flash, BF16 evaluation (HyPLM report)Protocol: GO-CC (HyPLM report)
Dataset: GO cellular component, DeepFRI split via SaProt (HyPLM report)
0.538 F1 max (Protein-centric Fmax over Gene Ontology cellular-component terms on the DeepFRI GO split as packaged by SaProt)
fraction · higher

Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyPLM-Flash on go-cc (HyPLM report)

hyplm-flash-20261106-protocol-go-cc

Aggregation: Not reported

HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 6, row 'GO-CC', column 'HyPLM-Flash' (page 12 of 13)
Configuration: HyPLM-Flash, BF16 evaluation (HyPLM report)Protocol: GO-MF (HyPLM report)
Dataset: GO molecular function, DeepFRI split via SaProt (HyPLM report)
0.661 F1 max (Protein-centric Fmax over Gene Ontology molecular-function terms on the DeepFRI GO split as packaged by SaProt)
fraction · higher

Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyPLM-Flash on go-mf (HyPLM report)

hyplm-flash-20261106-protocol-go-mf

Aggregation: Not reported

HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 6, row 'GO-MF', column 'HyPLM-Flash' (page 12 of 13)
Configuration: HyPLM-Flash, BF16 evaluation (HyPLM report)Protocol: HumanPPI (HyPLM report)
Dataset: HumanPPI via PEER (HyPLM report)
0.817 Accuracy (Human protein-protein interaction classification accuracy on PEER HumanPPI, with pair features [a, b, a*b, |a-b|])
fraction · higher

Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyPLM-Flash on humanppi (HyPLM report)

hyplm-flash-20261106-protocol-humanppi

Aggregation: Not reported

HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 6, row 'HumanPPI', column 'HyPLM-Flash' (page 12 of 13)
Configuration: HyPLM-Flash, BF16 evaluation (HyPLM report)Protocol: Hydrolase to P06241 (HyPLM report)
Dataset: Hydrolase to P06241 (FLIP2 cross-protein, HyPLM report)
−0.192 Spearman (Spearman correlation on the FLIP2 cross-protein hydrolase split, training on other hydrolases and testing on P06241)
unitless · higher

Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyPLM-Flash on hydrolase-to-p06241 (HyPLM report)

hyplm-flash-20261106-protocol-hydrolase-to-p06241

Aggregation: Not reported

HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 6, row 'Hydrolase to P06241', column 'HyPLM-Flash' (page 12 of 13)
Configuration: HyPLM-Flash, BF16 evaluation (HyPLM report)Protocol: Localization, 10-class (HyPLM report)
Dataset: DeepLoc ten-class localisation via PEER (HyPLM report)
0.794 Accuracy (Ten-class subcellular localisation accuracy on DeepLoc 1.0 via PEER)
fraction · higher

Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyPLM-Flash on localization-10-class (HyPLM report)

hyplm-flash-20261106-protocol-localization-10-class

Aggregation: Not reported

HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 6, row 'Localization, 10-class', column 'HyPLM-Flash' (page 12 of 13)
Configuration: HyPLM-Flash, BF16 evaluation (HyPLM report)Protocol: Localization, binary (HyPLM report)
Dataset: DeepLoc binary localisation via PEER (HyPLM report)
0.906 Accuracy (Binary localisation accuracy on DeepLoc 1.0 via PEER)
fraction · higher

Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyPLM-Flash on localization-binary (HyPLM report)

hyplm-flash-20261106-protocol-localization-binary

Aggregation: Not reported

HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 6, row 'Localization, binary', column 'HyPLM-Flash' (page 12 of 13)
Configuration: HyPLM-Flash, BF16 evaluation (HyPLM report)Protocol: Meltome human cell (HyPLM report)
Dataset subset: FLIP Thermostability, Human-Cell split (FLIP split)
0.684 Spearman (Spearman correlation on the FLIP Meltome human-cell split)
unitless · higher

Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyPLM-Flash on meltome-human-cell (HyPLM report)

hyplm-flash-20261106-protocol-meltome-human-cell

Aggregation: Not reported

HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 6, row 'Meltome human cell', column 'HyPLM-Flash' (page 12 of 13)
Configuration: HyPLM-Flash, BF16 evaluation (HyPLM report)Protocol: Meltome mixed (HyPLM report)
Dataset subset: FLIP Thermostability, Mixed split (FLIP split)
0.672 Spearman (Spearman correlation on the FLIP Meltome mixed split)
unitless · higher

Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyPLM-Flash on meltome-mixed (HyPLM report)

hyplm-flash-20261106-protocol-meltome-mixed

Aggregation: Not reported

HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 6, row 'Meltome mixed', column 'HyPLM-Flash' (page 12 of 13)
Configuration: HyPLM-Flash, BF16 evaluation (HyPLM report)Protocol: Metal-ion binding (HyPLM report)
Dataset: Metal-ion binding, SaProt packaging (HyPLM report)
0.695 Accuracy (Metal-ion binding classification accuracy on the split packaged by SaProt)
fraction · higher

Uncertainty: Not reported by the source: Section 4 says intervals are paired bootstrap intervals; none is printed here.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyPLM-Flash on metal-ion-binding (HyPLM report)

hyplm-flash-20261106-protocol-metal-ion-binding

Aggregation: Not reported

HyPLM Technical Report (Hyra Team, 2026-10-12) · Table 6, row 'Metal-ion binding', column 'HyPLM-Flash' (page 12 of 13)

Source checking is not independent reproduction. Release 2026-11-21-c8bea25e5abb.

Use this configuration

How it works, versions and access

Additional methodological details, versions and access terms have not yet been extracted into a structured profile for this configuration. Consult the linked sources and evaluation records below.

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

Evidence table

Inspect claims, sources and review details

Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.

One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.

0 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-11-21-c8bea25e5abb
Property and statementOriginal source and locationReview and provenance

No evidence rows match these filters. Choose another scope or clear the search.

Sources and history

Release 2026-11-21-c8bea25e5abb · Record review: source checked

2 source records and release historyDownload this release (gzip)
Technical metadata and record identifiers

Technical metadata for this record is tracked under stable ID hyplm-flash-20261106-config-hyplm-flash-bf16-evaluation.

Source locator: Section 3 'Accuracy in this report is evaluated with BF16 arithmetic'; Section 4; Appendix A

Related records

How to cite

HyPLM-Flash, BF16 evaluation (HyPLM report). Rewire biological model benchmark database, release 2026-11-21-c8bea25e5abb. https://benchmarks.rewirebio.io/database/configuration/hyplm-flash-20261106-config-hyplm-flash-bf16-evaluation/

Release 2026-11-21-c8bea25e5abb. Rankings and values change between releases, so keep the release id in the citation. Cite the original publication as well for any value you reuse: each result links its source.

The compilation and annotations made by Rewire in this release are offered under CC BY 4.0; values and text taken from cited sources stay under the terms of those sources and are not covered by this licence. Data licence

Suggest a correction