rewirebio.iobenchmarks
Source

GENEB: Why Genomic Models Are Hard to Compare

2606.04525v1

Original source

What this source contributed

Records in this release that cite this source. A record can cite several sources.

Results

Values as the source printed them. Compare results only under compatible protocols, datasets and metrics.

Model or configurationMetricValueDatasetEvaluation
GENA-LM-Large-T2TMacro MCC0.530 unitlessGENEB representative task subset (GENEB split)GENA-LM-Large-T2T on GENEB LINEAR-PROBE: Average macro-MCC across the 13 representative tasks, linear probe
GENA-LM-Large-T2TMacro MCC0.535 unitlessGENEB representative task subset (GENEB split)GENA-LM-Large-T2T on GENEB MLP-PROBE: Average macro-MCC across the 13 representative tasks, MLP probe
GENERator-Eukaryote-1.2BMacro MCC0.579 unitlessGENEB representative task subset (GENEB split)GENERator-Eukaryote-1.2B on GENEB LINEAR-PROBE: Average macro-MCC across the 13 representative tasks, linear probe
GENERator-Eukaryote-1.2BMacro MCC0.595 unitlessGENEB representative task subset (GENEB split)GENERator-Eukaryote-1.2B on GENEB MLP-PROBE: Average macro-MCC across the 13 representative tasks, MLP probe
GENERator-Eukaryote-3BMacro MCC0.605 unitlessGENEB representative task subset (GENEB split)GENERator-Eukaryote-3B on GENEB LINEAR-PROBE: Average macro-MCC across the 13 representative tasks, linear probe
GENERator-Eukaryote-3BMacro MCC0.609 unitlessGENEB representative task subset (GENEB split)GENERator-Eukaryote-3B on GENEB MLP-PROBE: Average macro-MCC across the 13 representative tasks, MLP probe
GenomeOcean-4BMacro MCC0.552 unitlessGENEB representative task subset (GENEB split)GenomeOcean-4B on GENEB LINEAR-PROBE: Average macro-MCC across the 13 representative tasks, linear probe
GenomeOcean-4BMacro MCC0.552 unitlessGENEB representative task subset (GENEB split)GenomeOcean-4B on GENEB MLP-PROBE: Average macro-MCC across the 13 representative tasks, MLP probe
GenomeOcean-500MMacro MCC0.536 unitlessGENEB representative task subset (GENEB split)GenomeOcean-500M on GENEB LINEAR-PROBE: Average macro-MCC across the 13 representative tasks, linear probe
GenomeOcean-500MMacro MCC0.535 unitlessGENEB representative task subset (GENEB split)GenomeOcean-500M on GENEB MLP-PROBE: Average macro-MCC across the 13 representative tasks, MLP probe
GROVERMacro MCC0.466 unitlessGENEB representative task subset (GENEB split)GROVER on GENEB LINEAR-PROBE: Average macro-MCC across the 13 representative tasks, linear probe
GROVERMacro MCC0.477 unitlessGENEB representative task subset (GENEB split)GROVER on GENEB MLP-PROBE: Average macro-MCC across the 13 representative tasks, MLP probe
HyenaDNA-Large-1MMacro MCC0.427 unitlessGENEB representative task subset (GENEB split)HyenaDNA-Large-1M on GENEB LINEAR-PROBE: Average macro-MCC across the 13 representative tasks, linear probe
HyenaDNA-Large-1MMacro MCC0.479 unitlessGENEB representative task subset (GENEB split)HyenaDNA-Large-1M on GENEB MLP-PROBE: Average macro-MCC across the 13 representative tasks, MLP probe
LucaOneMacro MCC0.573 unitlessGENEB representative task subset (GENEB split)LucaOne on GENEB LINEAR-PROBE: Average macro-MCC across the 13 representative tasks, linear probe
LucaOneMacro MCC0.600 unitlessGENEB representative task subset (GENEB split)LucaOne on GENEB MLP-PROBE: Average macro-MCC across the 13 representative tasks, MLP probe
MutBERTMacro MCC0.516 unitlessGENEB representative task subset (GENEB split)MutBERT on GENEB LINEAR-PROBE: Average macro-MCC across the 13 representative tasks, linear probe
MutBERTMacro MCC0.517 unitlessGENEB representative task subset (GENEB split)MutBERT on GENEB MLP-PROBE: Average macro-MCC across the 13 representative tasks, MLP probe
NT-v2-50M-MSMacro MCC0.511 unitlessGENEB representative task subset (GENEB split)NT-v2-50M-MS on GENEB LINEAR-PROBE: Average macro-MCC across the 13 representative tasks, linear probe
NT-v2-50M-MSMacro MCC0.521 unitlessGENEB representative task subset (GENEB split)NT-v2-50M-MS on GENEB MLP-PROBE: Average macro-MCC across the 13 representative tasks, MLP probe
Omni-DNA-1BMacro MCC0.550 unitlessGENEB representative task subset (GENEB split)Omni-DNA-1B on GENEB LINEAR-PROBE: Average macro-MCC across the 13 representative tasks, linear probe
Omni-DNA-1BMacro MCC0.542 unitlessGENEB representative task subset (GENEB split)Omni-DNA-1B on GENEB MLP-PROBE: Average macro-MCC across the 13 representative tasks, MLP probe

Claims

Statements this source supports, each with where in the source it was checked.

  • GENEB leaderboard: part of GENEB: Part of GENEB (Both records describe the GENEB suite in the darlednik/GENEB repository at commit 9642d481e40c0af23995dcd162b779613f789f97: src-discovery-darlednik-geneb is README.md and lit-genomics-20261011-geneb-source-leaderboard is leaderboard/leaderboard.json at the same commit. The leaderboard record is the suite's published aggregate, not a separate benchmark.)
  • GENEB LINEAR-PROBE: part of discovery-benchmark-geneb: Part of GENEB (Table 8, column(Linear MCC))
  • GENEB MLP-PROBE: part of discovery-benchmark-geneb: Part of GENEB (Table 8, column(MLP MCC))
  • NT-v2-50M-MS: family Nucleotide Transformer: Family Nucleotide Transformer (mRNABench Table 2/Appendix model inventory; GenomeOcean Table 2; respective model methods; NABench model inventory; GENEB Table 8; source-labelled configuration NT-v2-50M-MS | Existing reviewed locator: Table 8, row(NT-v2-50M-MS))
  • NT-v2-50M-MS: family Nucleotide Transformer v2: Family Nucleotide Transformer v2 (GENEB Table 8 NT-v2-50M-MS; NABench model inventory N.T.v2 50M; official v2-50m-multi-species model card | Existing reviewed locator: Table 8, row(NT-v2-50M-MS))

Models, benchmarks and other records

Configurations (11)

Benchmarks (1)

Tasks (2)

Dataset subsets (1)

Evaluations (22)

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.

15 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
Artifact SHA-256
47975089c0ca738d5e2d6e6ea91cd4e7b80498c3f175803d8ec39ca77aa41629
Source metadata
GENEB: Why Genomic Models Are Hard to Compare

Original source ↗

No field-specific location recorded

Version: 2606.04525v1
Retrieved: 2026-09-17T07:56:09.460928+00:00

catalogued

No individual claim review recorded

Audit details

Field: attributes.artifact_sha256

Source artifact SHA-256: 47975089c0ca738d5e2d6e6ea91cd4e7b80498c3f175803d8ec39ca77aa41629

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

Artifact url
https://arxiv.org/html/2606.04525v1
Source metadata
GENEB: Why Genomic Models Are Hard to Compare

Original source ↗

No field-specific location recorded

Version: 2606.04525v1
Retrieved: 2026-09-17T07:56:09.460928+00:00

catalogued

No individual claim review recorded

Audit details

Field: attributes.artifact_url

Source artifact SHA-256: 47975089c0ca738d5e2d6e6ea91cd4e7b80498c3f175803d8ec39ca77aa41629

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

Hash scope
Exact retrieved primary paper artifact bytes.
Source metadata
GENEB: Why Genomic Models Are Hard to Compare

Original source ↗

No field-specific location recorded

Version: 2606.04525v1
Retrieved: 2026-09-17T07:56:09.460928+00:00

catalogued

No individual claim review recorded

Audit details

Field: attributes.hash_scope

Source artifact SHA-256: 47975089c0ca738d5e2d6e6ea91cd4e7b80498c3f175803d8ec39ca77aa41629

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

Retrieved at
2026-09-17T07:56:09.460928+00:00
Source metadata
GENEB: Why Genomic Models Are Hard to Compare

Original source ↗

No field-specific location recorded

Version: 2606.04525v1
Retrieved: 2026-09-17T07:56:09.460928+00:00

catalogued

No individual claim review recorded

Audit details

Field: attributes.retrieved_at

Source artifact SHA-256: 47975089c0ca738d5e2d6e6ea91cd4e7b80498c3f175803d8ec39ca77aa41629

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

Review method
1 values
  • automated-source-review
Source metadata
GENEB: Why Genomic Models Are Hard to Compare

Original source ↗

No field-specific location recorded

Version: 2606.04525v1
Retrieved: 2026-09-17T07:56:09.460928+00:00

catalogued

No individual claim review recorded

Audit details

Field: attributes.review.method

Source artifact SHA-256: 47975089c0ca738d5e2d6e6ea91cd4e7b80498c3f175803d8ec39ca77aa41629

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

Review: scope
Source identification and table transcription; no independent experimental reproduction.
Source metadata
GENEB: Why Genomic Models Are Hard to Compare

Original source ↗

No field-specific location recorded

Version: 2606.04525v1
Retrieved: 2026-09-17T07:56:09.460928+00:00

catalogued

No individual claim review recorded

Audit details

Field: attributes.review.scope

Source artifact SHA-256: 47975089c0ca738d5e2d6e6ea91cd4e7b80498c3f175803d8ec39ca77aa41629

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

Url
https://arxiv.org/html/2606.04525v1
Source metadata
GENEB: Why Genomic Models Are Hard to Compare

Original source ↗

No field-specific location recorded

Version: 2606.04525v1
Retrieved: 2026-09-17T07:56:09.460928+00:00

catalogued

No individual claim review recorded

Audit details

Field: attributes.url

Source artifact SHA-256: 47975089c0ca738d5e2d6e6ea91cd4e7b80498c3f175803d8ec39ca77aa41629

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

Version
2606.04525v1
Source metadata
GENEB: Why Genomic Models Are Hard to Compare

Original source ↗

No field-specific location recorded

Version: 2606.04525v1
Retrieved: 2026-09-17T07:56:09.460928+00:00

catalogued

No individual claim review recorded

Audit details

Field: attributes.version

Source artifact SHA-256: 47975089c0ca738d5e2d6e6ea91cd4e7b80498c3f175803d8ec39ca77aa41629

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

Description
Primary reference; inspect retrieval status and review scope.
Source metadata
GENEB: Why Genomic Models Are Hard to Compare

Original source ↗

No field-specific location recorded

Version: 2606.04525v1
Retrieved: 2026-09-17T07:56:09.460928+00:00

catalogued

No individual claim review recorded

Audit details

Field: description

Source artifact SHA-256: 47975089c0ca738d5e2d6e6ea91cd4e7b80498c3f175803d8ec39ca77aa41629

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

Search facets
None recorded
Source metadata
GENEB: Why Genomic Models Are Hard to Compare

Original source ↗

No field-specific location recorded

Version: 2606.04525v1
Retrieved: 2026-09-17T07:56:09.460928+00:00

catalogued

No individual claim review recorded

Audit details

Field: facets

Source artifact SHA-256: 47975089c0ca738d5e2d6e6ea91cd4e7b80498c3f175803d8ec39ca77aa41629

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

How to read the evidence

Sources and history

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

Primary reference; inspect retrieval status and review scope.

Release history

No supporting source is linked yet.

Read original source

Download this release (gzip)
Technical metadata and extraction receipts

Stable ID: evidence-expansion-p2-evidence-discovery-final-geneb-47975089c0ca

url
https://arxiv.org/html/2606.04525v1
version
2606.04525v1
retrieved at
2026-09-17T07:56:09.460928+00:00
artifact sha256
47975089c0ca738d5e2d6e6ea91cd4e7b80498c3f175803d8ec39ca77aa41629
artifact url
https://arxiv.org/html/2606.04525v1
hash scope
Exact retrieved primary paper artifact bytes.
review
scope: Source identification and table transcription; no independent experimental reproduction.; method: automated-source-review
Related records

    Suggest a correction