Configuration

Caduceus (GenBench)

Caduceus as fine-tuned in GenBench.

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.

Evaluations and results

52 evaluations · 55 results. Different protocols are not a single leaderboard.

Sorted by Accuracy (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 configuration	Protocol and dataset	Accuracy	Accuracy (task-level value as printed in Table 4)	Accuracy (task-level value as printed in Table 4; mean of the Table 10 dataset rows)	Pearson	MSE	AUROC	AUROC (mean of donor and acceptor as printed)	Pearson (mean of dev and hk as printed)	Spearman
Caduceus (GenBench)Evaluation	GenBench Long-range Promoters Prediction, GenBench Long-range Promoters Prediction	0.93 (best in column)	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Human Core Promoter Detection, dataset tata, GenBench Human Core Promoter Detection, dataset tata	0.875	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Human Core Promoter Detection, dataset notata, GenBench Human Core Promoter Detection, dataset notata	0.843	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Human Core Promoter Detection, dataset all, GenBench Human Core Promoter Detection, dataset all	0.834	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Human Promoter Detection, dataset notata, GenBench Human Promoter Detection, dataset notata	0.828	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Human Promoter Detection, dataset all, GenBench Human Promoter Detection, dataset all	0.783	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Human Transcription Factor Prediction, dataset 1, GenBench Human Transcription Factor Prediction, dataset 1	0.759	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Mouse Transcription Factor Prediction, dataset 2, GenBench Mouse Transcription Factor Prediction, dataset 2	0.749	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Mouse Transcription Factor Prediction, dataset 1, GenBench Mouse Transcription Factor Prediction, dataset 1	0.739	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Yeast Epigenetic Marks Prediction, dataset H3, GenBench Yeast Epigenetic Marks Prediction, dataset H3	0.715	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Human Transcription Factor Prediction, dataset 0, GenBench Human Transcription Factor Prediction, dataset 0	0.714	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Long-range Species Classification, GenBench Long-range Species Classification	0.711	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Yeast Epigenetic Marks Prediction, dataset H4, GenBench Yeast Epigenetic Marks Prediction, dataset H4	0.706	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Human Transcription Factor Prediction, dataset 4, GenBench Human Transcription Factor Prediction, dataset 4	0.689	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Human Transcription Factor Prediction, dataset 2, GenBench Human Transcription Factor Prediction, dataset 2	0.665	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Yeast Epigenetic Marks Prediction, dataset H3K79me3, GenBench Yeast Epigenetic Marks Prediction, dataset H3K79me3	0.659	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Yeast Epigenetic Marks Prediction, dataset H3K36me3, GenBench Yeast Epigenetic Marks Prediction, dataset H3K36me3	0.653	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Yeast Epigenetic Marks Prediction, dataset H3K14ac, GenBench Yeast Epigenetic Marks Prediction, dataset H3K14ac	0.646	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Yeast Epigenetic Marks Prediction, dataset H3K9ac, GenBench Yeast Epigenetic Marks Prediction, dataset H3K9ac	0.639	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Human Transcription Factor Prediction, dataset 3, GenBench Human Transcription Factor Prediction, dataset 3	0.637	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Yeast Epigenetic Marks Prediction, dataset H3K4me1, GenBench Yeast Epigenetic Marks Prediction, dataset H3K4me1	0.603	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Mouse Transcription Factor Prediction, dataset 0, GenBench Mouse Transcription Factor Prediction, dataset 0	0.601	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Yeast Epigenetic Marks Prediction, dataset H4ac, GenBench Yeast Epigenetic Marks Prediction, dataset H4ac	0.595	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Yeast Epigenetic Marks Prediction, dataset H3K4me2, GenBench Yeast Epigenetic Marks Prediction, dataset H3K4me2	0.594	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Mouse Transcription Factor Prediction, dataset 4, GenBench Mouse Transcription Factor Prediction, dataset 4	0.592	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Human Promoter Detection, dataset tata, GenBench Human Promoter Detection, dataset tata	0.585	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Mouse Transcription Factor Prediction, dataset 3, GenBench Mouse Transcription Factor Prediction, dataset 3	0.579	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Yeast Epigenetic Marks Prediction, dataset H3K4me3, GenBench Yeast Epigenetic Marks Prediction, dataset H3K4me3	0.57	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Bulk RNA expression, GenBench Bulk RNA expression	Not reported	Not reported	Not reported	Not reported	0.51	Not reported	Not reported	Not reported	0.746
Caduceus (GenBench)Evaluation	GenBench Drosophila enhancer activity (dev), GenBench Drosophila enhancer activity (dev)	Not reported	Not reported	Not reported	0.443	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Drosophila enhancer activity (hk), GenBench Drosophila enhancer activity (hk)	Not reported	Not reported	Not reported	0.53 (best in column)	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Drosophila enhancer activity (Mean), GenBench Drosophila enhancer activity (Mean)	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	0.486	Not reported
Caduceus (GenBench)Evaluation	GenBench Genomic structure prediction (H1-ESC), GenBench Genomic structure prediction (H1-ESC)	Not reported	Not reported	Not reported	0.502	0.0168 (best in column)	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Genomic structure prediction (HFF), GenBench Genomic structure prediction (HFF)	Not reported	Not reported	Not reported	0.354	0.105	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Long-range splice site prediction (Mean), GenBench Long-range splice site prediction (Mean)	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	0.691	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Long-range splice site prediction (Splice acceptor), GenBench Long-range splice site prediction (Splice acceptor)	Not reported	Not reported	Not reported	Not reported	Not reported	0.74 (best in column)	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Long-range splice site prediction (Splice donar), GenBench Long-range splice site prediction (Splice donar)	Not reported	Not reported	Not reported	Not reported	Not reported	0.642	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Coding vs Intergenomic, GenBench Coding vs Intergenomic	Not reported	0.937	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Human Core Promoter Detection, GenBench Human Core Promoter Detection	Not reported	Not reported	0.851 (best in column)	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Human Enhancers Cohn, GenBench Human Enhancers Cohn	Not reported	0.738	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Human Enhancers Ensembl, GenBench Human Enhancers Ensembl	Not reported	0.845	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Human Ensembl Regulatory, GenBench Human Ensembl Regulatory	Not reported	0.737	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Human Nontata Promoters, GenBench Human Nontata Promoters	Not reported	0.888	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Human OCR Ensembl, GenBench Human OCR Ensembl	Not reported	0.818	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Human Promoter Detection, GenBench Human Promoter Detection	Not reported	Not reported	0.732	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Human Splice Site Detection, GenBench Human Splice Site Detection	Not reported	0.567	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Human Transcription Factor Prediction, GenBench Human Transcription Factor Prediction	Not reported	Not reported	0.693	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Human vs Worm, GenBench Human vs Worm	Not reported	0.956 (best in column)	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Mouse Enhancers, GenBench Mouse Enhancers	Not reported	0.816	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Mouse Transcription Factor Prediction, GenBench Mouse Transcription Factor Prediction	Not reported	Not reported	0.652	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Virus Covid Variant Classification, GenBench Virus Covid Variant Classification	Not reported	0.379	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Caduceus (GenBench)Evaluation	GenBench Yeast Epigenetic Marks Prediction, GenBench Yeast Epigenetic Marks Prediction	Not reported	Not reported	0.638	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported

All 55 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.

Use this configuration

How it works, versions and access

Strengths, limitations and unresolved questions

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 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance

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

How to read the evidence

Sources and history

Release 2026-10-22-1b7cf027e4f6 · Record review: source checked

1 source record and release history

GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models · Original source · arXiv 2406.01627 version 2

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: lit-genomics-20261011-genbench-config-caduceus

areas: dna-genomes
contexts: research
method types: foundation_model
reported name: Caduceus
foundation model eligible: true
parameters: 7.9M parameters (Table 9); fine-tuned 100 epochs, AdamW, cosine decay
access reuse: Public checkpoint
source locator: Table 9; table headers
missing metadata: version: reason: unreported; note: Checkpoint name not printed; parameter count only

Related records

Suggest a correction

Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: Caduceus (GenBench)	Protocol: GenBench Bulk RNA expression Dataset: GenBench Bulk RNA expression	0.51 MSE unitless · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus on GenBench Bulk RNA expression lit-genomics-20261011-genbench-protocol-bulk-rna-expression Aggregation: Not reported GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models · Table 8, row 'Bulk RNA expression', column 'Caduceus MSE'
Configuration: Caduceus (GenBench)	Protocol: GenBench Bulk RNA expression Dataset: GenBench Bulk RNA expression	0.746 Spearman unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus on GenBench Bulk RNA expression lit-genomics-20261011-genbench-protocol-bulk-rna-expression Aggregation: Not reported GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models · Table 8, row 'Bulk RNA expression', column 'Caduceus Spearman'
Configuration: Caduceus (GenBench)	Protocol: GenBench Drosophila enhancer activity (dev) Dataset: GenBench Drosophila enhancer activity (dev)	0.443 Pearson unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus on GenBench Drosophila enhancer activity (dev) lit-genomics-20261011-genbench-protocol-drosophila-enhancer-activity-dev Aggregation: Not reported GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models · Table 3, row 'Drosophila enhancer activity (dev)', column 'Caduceus'
Configuration: Caduceus (GenBench)	Protocol: GenBench Drosophila enhancer activity (hk) Dataset: GenBench Drosophila enhancer activity (hk)	0.53 Pearson unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus on GenBench Drosophila enhancer activity (hk) lit-genomics-20261011-genbench-protocol-drosophila-enhancer-activity-hk Aggregation: Not reported GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models · Table 3, row 'Drosophila enhancer activity (hk)', column 'Caduceus'
Configuration: Caduceus (GenBench)	Protocol: GenBench Drosophila enhancer activity (Mean) Dataset: GenBench Drosophila enhancer activity (Mean)	0.486 Pearson (mean of dev and hk as printed) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus on GenBench Drosophila enhancer activity (Mean) lit-genomics-20261011-genbench-protocol-drosophila-enhancer-activity-mean Aggregation: Not reported GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models · Table 3, row 'Drosophila enhancer activity (Mean)', column 'Caduceus'
Configuration: Caduceus (GenBench)	Protocol: GenBench Genomic structure prediction (H1-ESC) Dataset: GenBench Genomic structure prediction (H1-ESC)	0.0168 MSE unitless · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus on GenBench Genomic structure prediction (H1-ESC) lit-genomics-20261011-genbench-protocol-genome-structure-h1-esc Aggregation: Not reported GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models · Table 7, row 'Genomic structure prediction (H1-ESC)', column 'Caduceus MSE'
Configuration: Caduceus (GenBench)	Protocol: GenBench Genomic structure prediction (H1-ESC) Dataset: GenBench Genomic structure prediction (H1-ESC)	0.502 Pearson unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus on GenBench Genomic structure prediction (H1-ESC) lit-genomics-20261011-genbench-protocol-genome-structure-h1-esc Aggregation: Not reported GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models · Table 7, row 'Genomic structure prediction (H1-ESC)', column 'Caduceus Pearson'
Configuration: Caduceus (GenBench)	Protocol: GenBench Genomic structure prediction (HFF) Dataset: GenBench Genomic structure prediction (HFF)	0.105 MSE unitless · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus on GenBench Genomic structure prediction (HFF) lit-genomics-20261011-genbench-protocol-genome-structure-hff Aggregation: Not reported GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models · Table 7, row 'Genomic structure prediction (HFF)', column 'Caduceus MSE'
Configuration: Caduceus (GenBench)	Protocol: GenBench Genomic structure prediction (HFF) Dataset: GenBench Genomic structure prediction (HFF)	0.354 Pearson unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus on GenBench Genomic structure prediction (HFF) lit-genomics-20261011-genbench-protocol-genome-structure-hff Aggregation: Not reported GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models · Table 7, row 'Genomic structure prediction (HFF)', column 'Caduceus Pearson'
Configuration: Caduceus (GenBench)	Protocol: GenBench Long-range Promoters Prediction Dataset: GenBench Long-range Promoters Prediction	0.93 Accuracy fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus on GenBench Long-range Promoters Prediction lit-genomics-20261011-genbench-protocol-long-promoters-prediction Aggregation: Not reported GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models · Table 6, row 'Long-range Promoters Prediction', column 'Caduceus'
Configuration: Caduceus (GenBench)	Protocol: GenBench Long-range Species Classification Dataset: GenBench Long-range Species Classification	0.711 Accuracy fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus on GenBench Long-range Species Classification lit-genomics-20261011-genbench-protocol-long-species-classification Aggregation: Not reported GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models · Table 6, row 'Long-range Species Classification', column 'Caduceus'
Configuration: Caduceus (GenBench)	Protocol: GenBench Long-range splice site prediction (Mean) Dataset: GenBench Long-range splice site prediction (Mean)	0.691 AUROC (mean of donor and acceptor as printed) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus on GenBench Long-range splice site prediction (Mean) lit-genomics-20261011-genbench-protocol-long-splice-mean Aggregation: Not reported GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models · Table 5, row 'Long-range splice site prediction (Mean)', column 'Caduceus'
Configuration: Caduceus (GenBench)	Protocol: GenBench Long-range splice site prediction (Splice acceptor) Dataset: GenBench Long-range splice site prediction (Splice acceptor)	0.74 AUROC unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus on GenBench Long-range splice site prediction (Splice acceptor) lit-genomics-20261011-genbench-protocol-long-splice-splice-acceptor Aggregation: Not reported GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models · Table 5, row 'Long-range splice site prediction (Splice acceptor)', column 'Caduceus'
Configuration: Caduceus (GenBench)	Protocol: GenBench Long-range splice site prediction (Splice donar) Dataset: GenBench Long-range splice site prediction (Splice donar)	0.642 AUROC unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus on GenBench Long-range splice site prediction (Splice donar) lit-genomics-20261011-genbench-protocol-long-splice-splice-donar Aggregation: Not reported GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models · Table 5, row 'Long-range splice site prediction (Splice donar)', column 'Caduceus'
Configuration: Caduceus (GenBench)	Protocol: GenBench Coding vs Intergenomic Dataset: GenBench Coding vs Intergenomic	0.937 Accuracy (task-level value as printed in Table 4) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus on GenBench Coding vs Intergenomic lit-genomics-20261011-genbench-protocol-short-coding-vs-intergenomic Aggregation: Not reported GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models · Table 4, row 'Coding vs Intergenomic', column 'Caduceus'
Configuration: Caduceus (GenBench)	Protocol: GenBench Human Core Promoter Detection Dataset: GenBench Human Core Promoter Detection	0.851 Accuracy (task-level value as printed in Table 4; mean of the Table 10 dataset rows) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus on GenBench Human Core Promoter Detection lit-genomics-20261011-genbench-protocol-short-human-core-promoter-detection Aggregation: Not reported GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models · Table 4, row 'Human Core Promoter Detection', column 'Caduceus'
Configuration: Caduceus (GenBench)	Protocol: GenBench Human Core Promoter Detection, dataset all Dataset: GenBench Human Core Promoter Detection, dataset all	0.834 Accuracy fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus on GenBench Human Core Promoter Detection, dataset all lit-genomics-20261011-genbench-protocol-short-human-core-promoter-detection-all Aggregation: Not reported GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models · Table 10, row 'Human Core Promoter Detection, dataset all', column 'Caduceus'
Configuration: Caduceus (GenBench)	Protocol: GenBench Human Core Promoter Detection, dataset notata Dataset: GenBench Human Core Promoter Detection, dataset notata	0.843 Accuracy fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus on GenBench Human Core Promoter Detection, dataset notata lit-genomics-20261011-genbench-protocol-short-human-core-promoter-detection-notata Aggregation: Not reported GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models · Table 10, row 'Human Core Promoter Detection, dataset notata', column 'Caduceus'
Configuration: Caduceus (GenBench)	Protocol: GenBench Human Core Promoter Detection, dataset tata Dataset: GenBench Human Core Promoter Detection, dataset tata	0.875 Accuracy fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus on GenBench Human Core Promoter Detection, dataset tata lit-genomics-20261011-genbench-protocol-short-human-core-promoter-detection-tata Aggregation: Not reported GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models · Table 10, row 'Human Core Promoter Detection, dataset tata', column 'Caduceus'
Configuration: Caduceus (GenBench)	Protocol: GenBench Human Enhancers Cohn Dataset: GenBench Human Enhancers Cohn	0.738 Accuracy (task-level value as printed in Table 4) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus on GenBench Human Enhancers Cohn lit-genomics-20261011-genbench-protocol-short-human-enhancers-cohn Aggregation: Not reported GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models · Table 4, row 'Human Enhancers Cohn', column 'Caduceus'
Configuration: Caduceus (GenBench)	Protocol: GenBench Human Enhancers Ensembl Dataset: GenBench Human Enhancers Ensembl	0.845 Accuracy (task-level value as printed in Table 4) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus on GenBench Human Enhancers Ensembl lit-genomics-20261011-genbench-protocol-short-human-enhancers-ensembl Aggregation: Not reported GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models · Table 4, row 'Human Enhancers Ensembl', column 'Caduceus'
Configuration: Caduceus (GenBench)	Protocol: GenBench Human Ensembl Regulatory Dataset: GenBench Human Ensembl Regulatory	0.737 Accuracy (task-level value as printed in Table 4) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus on GenBench Human Ensembl Regulatory lit-genomics-20261011-genbench-protocol-short-human-ensembl-regulatory Aggregation: Not reported GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models · Table 4, row 'Human Ensembl Regulatory', column 'Caduceus'
Configuration: Caduceus (GenBench)	Protocol: GenBench Human Nontata Promoters Dataset: GenBench Human Nontata Promoters	0.888 Accuracy (task-level value as printed in Table 4) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus on GenBench Human Nontata Promoters lit-genomics-20261011-genbench-protocol-short-human-nontata-promoters Aggregation: Not reported GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models · Table 4, row 'Human Nontata Promoters', column 'Caduceus'
Configuration: Caduceus (GenBench)	Protocol: GenBench Human OCR Ensembl Dataset: GenBench Human OCR Ensembl	0.818 Accuracy (task-level value as printed in Table 4) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus on GenBench Human OCR Ensembl lit-genomics-20261011-genbench-protocol-short-human-ocr-ensembl Aggregation: Not reported GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models · Table 4, row 'Human OCR Ensembl', column 'Caduceus'
Configuration: Caduceus (GenBench)	Protocol: GenBench Human Promoter Detection Dataset: GenBench Human Promoter Detection	0.732 Accuracy (task-level value as printed in Table 4; mean of the Table 10 dataset rows) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus on GenBench Human Promoter Detection lit-genomics-20261011-genbench-protocol-short-human-promoter-detection Aggregation: Not reported GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models · Table 4, row 'Human Promoter Detection', column 'Caduceus'