Configuration

Caduceus-Ps (zero-shot, GFMBench-API)

Caduceus-Ps: About 7M parameters; Hugging Face checkpoint; zero-shot.

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

18 evaluations · 72 results. Different protocols are not a single leaderboard.

Sorted by AUPRC (zero-shot; cosine similarity of reference and alternate sequence embeddings) (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	AUPRC (zero-shot; cosine similarity of reference and alternate sequence embeddings)	AUPRC (zero-shot; L2 distance of reference and alternate sequence embeddings)	AUROC (zero-shot; cosine similarity of reference and alternate sequence embeddings)	AUROC (zero-shot; L2 distance of reference and alternate sequence embeddings)	AUPRC (zero-shot; cosine similarity of embeddings at the SNV position)	AUPRC (zero-shot; masked log-likelihood ratio)	AUROC (zero-shot; cosine similarity of embeddings at the SNV position)	AUROC (zero-shot; masked log-likelihood ratio)
Caduceus-Ps (zero-shot, GFMBench-API)Evaluation	GFMBench-API Songlab ClinVar, zs-embedding, Songlab ClinVar test set (GFMBench-API)	0.996 (best in column)	0.991 (best in column)	0.933 (best in column)	0.867 (best in column)	0.991 (best in column)	Not reported	0.867 (best in column)	Not reported
Caduceus-Ps (zero-shot, GFMBench-API)Evaluation	GFMBench-API ClinVar Indel Pathogenicity, zs-embedding, ClinVar Indel Pathogenicity test set (GFMBench-API)	0.958	0.959	0.708	0.71	Not reported	Not reported	Not reported	Not reported
Caduceus-Ps (zero-shot, GFMBench-API)Evaluation	GFMBench-API VEP-eval, zs-embedding, VEP-eval test set (GFMBench-API)	0.556	0.563	0.702	0.707	0.363	Not reported	0.511	Not reported
Caduceus-Ps (zero-shot, GFMBench-API)Evaluation	GFMBench-API Bend Variant Effects Disease, zs-embedding, Bend Variant Effects Disease test set (GFMBench-API)	0.378	0.379	0.772	0.78	0.107	Not reported	0.545	Not reported
Caduceus-Ps (zero-shot, GFMBench-API)Evaluation	GFMBench-API BRCA1, zs-embedding, BRCA1 test set (GFMBench-API)	0.291	0.299	0.555	0.563	0.203	Not reported	0.469	Not reported
Caduceus-Ps (zero-shot, GFMBench-API)Evaluation	GFMBench-API TraitGym Complex, zs-embedding, TraitGym Complex test set (GFMBench-API)	0.0946	0.0974	0.483	0.497	0.103	Not reported	0.518	Not reported
Caduceus-Ps (zero-shot, GFMBench-API)Evaluation	GFMBench-API TraitGym Mendelian, zs-embedding, TraitGym Mendelian test set (GFMBench-API)	0.0879	0.0922	0.463	0.477	0.127	Not reported	0.553	Not reported
Caduceus-Ps (zero-shot, GFMBench-API)Evaluation	GFMBench-API LOL-EVE, zs-embedding, LOL-EVE test set (GFMBench-API)	0.0861	0.0863	0.524	0.522	Not reported	Not reported	Not reported	Not reported
Caduceus-Ps (zero-shot, GFMBench-API)Evaluation	GFMBench-API Bend Variant Effects Expression, zs-embedding, Bend Variant Effects Expression test set (GFMBench-API)	0.0676	0.0692	0.473	0.479	0.0775	Not reported	0.537	Not reported
Caduceus-Ps (zero-shot, GFMBench-API)Evaluation	GFMBench-API LRB Variant Effect OMIM, zs-embedding, LRB Variant Effect OMIM test set (GFMBench-API)	0.0019	0.0019	0.486	0.49	0.0022	Not reported	0.524	Not reported
Caduceus-Ps (zero-shot, GFMBench-API)Evaluation	GFMBench-API Bend Variant Effects Disease, zs-mlm-llr, Bend Variant Effects Disease test set (GFMBench-API)	Not reported	Not reported	Not reported	Not reported	Not reported	0.14	Not reported	0.66
Caduceus-Ps (zero-shot, GFMBench-API)Evaluation	GFMBench-API Bend Variant Effects Expression, zs-mlm-llr, Bend Variant Effects Expression test set (GFMBench-API)	Not reported	Not reported	Not reported	Not reported	Not reported	0.0679	Not reported	0.489
Caduceus-Ps (zero-shot, GFMBench-API)Evaluation	GFMBench-API BRCA1, zs-mlm-llr, BRCA1 test set (GFMBench-API)	Not reported	Not reported	Not reported	Not reported	Not reported	0.218	Not reported	0.483
Caduceus-Ps (zero-shot, GFMBench-API)Evaluation	GFMBench-API LRB Variant Effect OMIM, zs-mlm-llr, LRB Variant Effect OMIM test set (GFMBench-API)	Not reported	Not reported	Not reported	Not reported	Not reported	0.0016	Not reported	0.41
Caduceus-Ps (zero-shot, GFMBench-API)Evaluation	GFMBench-API Songlab ClinVar, zs-mlm-llr, Songlab ClinVar test set (GFMBench-API)	Not reported	Not reported	Not reported	Not reported	Not reported	0.546 (best in column)	Not reported	0.522
Caduceus-Ps (zero-shot, GFMBench-API)Evaluation	GFMBench-API TraitGym Complex, zs-mlm-llr, TraitGym Complex test set (GFMBench-API)	Not reported	Not reported	Not reported	Not reported	Not reported	0.0923	Not reported	0.483
Caduceus-Ps (zero-shot, GFMBench-API)Evaluation	GFMBench-API TraitGym Mendelian, zs-mlm-llr, TraitGym Mendelian test set (GFMBench-API)	Not reported	Not reported	Not reported	Not reported	Not reported	0.0929	Not reported	0.505
Caduceus-Ps (zero-shot, GFMBench-API)Evaluation	GFMBench-API VEP-eval, zs-mlm-llr, VEP-eval test set (GFMBench-API)	Not reported	Not reported	Not reported	Not reported	Not reported	0.478	Not reported	0.662 (best in column)

All 72 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: Caduceus-Ps (zero-shot, GFMBench-API)	Protocol: GFMBench-API Bend Variant Effects Disease, zs-embedding Dataset: Bend Variant Effects Disease test set (GFMBench-API)	0.378 AUPRC (zero-shot; cosine similarity of reference and alternate sequence embeddings) 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-Ps on GFMBench-API Bend Variant Effects Disease (zs-embedding) lit-genomics-20261011-gfmbench-protocol-bend-variant-effects-disease-zs-embedding Aggregation: Not reported GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models · Table 3, task 'Bend Variant Effects Disease', row 'Caduceus-Ps', column 'Cos AUPRC'
Configuration: Caduceus-Ps (zero-shot, GFMBench-API)	Protocol: GFMBench-API Bend Variant Effects Disease, zs-embedding Dataset: Bend Variant Effects Disease test set (GFMBench-API)	0.772 AUROC (zero-shot; cosine similarity of reference and alternate sequence embeddings) 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-Ps on GFMBench-API Bend Variant Effects Disease (zs-embedding) lit-genomics-20261011-gfmbench-protocol-bend-variant-effects-disease-zs-embedding Aggregation: Not reported GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models · Table 3, task 'Bend Variant Effects Disease', row 'Caduceus-Ps', column 'Cos AUROC'
Configuration: Caduceus-Ps (zero-shot, GFMBench-API)	Protocol: GFMBench-API Bend Variant Effects Disease, zs-embedding Dataset: Bend Variant Effects Disease test set (GFMBench-API)	0.379 AUPRC (zero-shot; L2 distance of reference and alternate sequence embeddings) 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-Ps on GFMBench-API Bend Variant Effects Disease (zs-embedding) lit-genomics-20261011-gfmbench-protocol-bend-variant-effects-disease-zs-embedding Aggregation: Not reported GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models · Table 3, task 'Bend Variant Effects Disease', row 'Caduceus-Ps', column 'L2 AUPRC'
Configuration: Caduceus-Ps (zero-shot, GFMBench-API)	Protocol: GFMBench-API Bend Variant Effects Disease, zs-embedding Dataset: Bend Variant Effects Disease test set (GFMBench-API)	0.78 AUROC (zero-shot; L2 distance of reference and alternate sequence embeddings) 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-Ps on GFMBench-API Bend Variant Effects Disease (zs-embedding) lit-genomics-20261011-gfmbench-protocol-bend-variant-effects-disease-zs-embedding Aggregation: Not reported GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models · Table 3, task 'Bend Variant Effects Disease', row 'Caduceus-Ps', column 'L2 AUROC'
Configuration: Caduceus-Ps (zero-shot, GFMBench-API)	Protocol: GFMBench-API Bend Variant Effects Disease, zs-embedding Dataset: Bend Variant Effects Disease test set (GFMBench-API)	0.107 AUPRC (zero-shot; cosine similarity of embeddings at the SNV position) 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-Ps on GFMBench-API Bend Variant Effects Disease (zs-embedding) lit-genomics-20261011-gfmbench-protocol-bend-variant-effects-disease-zs-embedding Aggregation: Not reported GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models · Table 3, task 'Bend Variant Effects Disease', row 'Caduceus-Ps', column 'SNV Cos AUPRC'
Configuration: Caduceus-Ps (zero-shot, GFMBench-API)	Protocol: GFMBench-API Bend Variant Effects Disease, zs-embedding Dataset: Bend Variant Effects Disease test set (GFMBench-API)	0.545 AUROC (zero-shot; cosine similarity of embeddings at the SNV position) 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-Ps on GFMBench-API Bend Variant Effects Disease (zs-embedding) lit-genomics-20261011-gfmbench-protocol-bend-variant-effects-disease-zs-embedding Aggregation: Not reported GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models · Table 3, task 'Bend Variant Effects Disease', row 'Caduceus-Ps', column 'SNV Cos AUROC'
Configuration: Caduceus-Ps (zero-shot, GFMBench-API)	Protocol: GFMBench-API Bend Variant Effects Disease, zs-mlm-llr Dataset: Bend Variant Effects Disease test set (GFMBench-API)	0.14 AUPRC (zero-shot; masked log-likelihood ratio) 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-Ps on GFMBench-API Bend Variant Effects Disease (zs-mlm-llr) lit-genomics-20261011-gfmbench-protocol-bend-variant-effects-disease-zs-mlm-llr Aggregation: Not reported GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models · Table 4, task 'Bend Variant Effects Disease', row 'Caduceus-Ps', column 'Msk LLR PRC'
Configuration: Caduceus-Ps (zero-shot, GFMBench-API)	Protocol: GFMBench-API Bend Variant Effects Disease, zs-mlm-llr Dataset: Bend Variant Effects Disease test set (GFMBench-API)	0.66 AUROC (zero-shot; masked log-likelihood ratio) 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-Ps on GFMBench-API Bend Variant Effects Disease (zs-mlm-llr) lit-genomics-20261011-gfmbench-protocol-bend-variant-effects-disease-zs-mlm-llr Aggregation: Not reported GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models · Table 4, task 'Bend Variant Effects Disease', row 'Caduceus-Ps', column 'Msk LLR ROC'
Configuration: Caduceus-Ps (zero-shot, GFMBench-API)	Protocol: GFMBench-API Bend Variant Effects Expression, zs-embedding Dataset: Bend Variant Effects Expression test set (GFMBench-API)	0.0676 AUPRC (zero-shot; cosine similarity of reference and alternate sequence embeddings) 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-Ps on GFMBench-API Bend Variant Effects Expression (zs-embedding) lit-genomics-20261011-gfmbench-protocol-bend-variant-effects-expression-zs-embedding Aggregation: Not reported GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models · Table 3, task 'Bend Variant Effects Expression', row 'Caduceus-Ps', column 'Cos AUPRC'
Configuration: Caduceus-Ps (zero-shot, GFMBench-API)	Protocol: GFMBench-API Bend Variant Effects Expression, zs-embedding Dataset: Bend Variant Effects Expression test set (GFMBench-API)	0.473 AUROC (zero-shot; cosine similarity of reference and alternate sequence embeddings) 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-Ps on GFMBench-API Bend Variant Effects Expression (zs-embedding) lit-genomics-20261011-gfmbench-protocol-bend-variant-effects-expression-zs-embedding Aggregation: Not reported GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models · Table 3, task 'Bend Variant Effects Expression', row 'Caduceus-Ps', column 'Cos AUROC'
Configuration: Caduceus-Ps (zero-shot, GFMBench-API)	Protocol: GFMBench-API Bend Variant Effects Expression, zs-embedding Dataset: Bend Variant Effects Expression test set (GFMBench-API)	0.0692 AUPRC (zero-shot; L2 distance of reference and alternate sequence embeddings) 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-Ps on GFMBench-API Bend Variant Effects Expression (zs-embedding) lit-genomics-20261011-gfmbench-protocol-bend-variant-effects-expression-zs-embedding Aggregation: Not reported GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models · Table 3, task 'Bend Variant Effects Expression', row 'Caduceus-Ps', column 'L2 AUPRC'
Configuration: Caduceus-Ps (zero-shot, GFMBench-API)	Protocol: GFMBench-API Bend Variant Effects Expression, zs-embedding Dataset: Bend Variant Effects Expression test set (GFMBench-API)	0.479 AUROC (zero-shot; L2 distance of reference and alternate sequence embeddings) 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-Ps on GFMBench-API Bend Variant Effects Expression (zs-embedding) lit-genomics-20261011-gfmbench-protocol-bend-variant-effects-expression-zs-embedding Aggregation: Not reported GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models · Table 3, task 'Bend Variant Effects Expression', row 'Caduceus-Ps', column 'L2 AUROC'
Configuration: Caduceus-Ps (zero-shot, GFMBench-API)	Protocol: GFMBench-API Bend Variant Effects Expression, zs-embedding Dataset: Bend Variant Effects Expression test set (GFMBench-API)	0.0775 AUPRC (zero-shot; cosine similarity of embeddings at the SNV position) 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-Ps on GFMBench-API Bend Variant Effects Expression (zs-embedding) lit-genomics-20261011-gfmbench-protocol-bend-variant-effects-expression-zs-embedding Aggregation: Not reported GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models · Table 3, task 'Bend Variant Effects Expression', row 'Caduceus-Ps', column 'SNV Cos AUPRC'
Configuration: Caduceus-Ps (zero-shot, GFMBench-API)	Protocol: GFMBench-API Bend Variant Effects Expression, zs-embedding Dataset: Bend Variant Effects Expression test set (GFMBench-API)	0.537 AUROC (zero-shot; cosine similarity of embeddings at the SNV position) 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-Ps on GFMBench-API Bend Variant Effects Expression (zs-embedding) lit-genomics-20261011-gfmbench-protocol-bend-variant-effects-expression-zs-embedding Aggregation: Not reported GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models · Table 3, task 'Bend Variant Effects Expression', row 'Caduceus-Ps', column 'SNV Cos AUROC'
Configuration: Caduceus-Ps (zero-shot, GFMBench-API)	Protocol: GFMBench-API Bend Variant Effects Expression, zs-mlm-llr Dataset: Bend Variant Effects Expression test set (GFMBench-API)	0.0679 AUPRC (zero-shot; masked log-likelihood ratio) 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-Ps on GFMBench-API Bend Variant Effects Expression (zs-mlm-llr) lit-genomics-20261011-gfmbench-protocol-bend-variant-effects-expression-zs-mlm-llr Aggregation: Not reported GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models · Table 4, task 'Bend Variant Effects Expression', row 'Caduceus-Ps', column 'Msk LLR PRC'
Configuration: Caduceus-Ps (zero-shot, GFMBench-API)	Protocol: GFMBench-API Bend Variant Effects Expression, zs-mlm-llr Dataset: Bend Variant Effects Expression test set (GFMBench-API)	0.489 AUROC (zero-shot; masked log-likelihood ratio) 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-Ps on GFMBench-API Bend Variant Effects Expression (zs-mlm-llr) lit-genomics-20261011-gfmbench-protocol-bend-variant-effects-expression-zs-mlm-llr Aggregation: Not reported GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models · Table 4, task 'Bend Variant Effects Expression', row 'Caduceus-Ps', column 'Msk LLR ROC'
Configuration: Caduceus-Ps (zero-shot, GFMBench-API)	Protocol: GFMBench-API BRCA1, zs-embedding Dataset: BRCA1 test set (GFMBench-API)	0.291 AUPRC (zero-shot; cosine similarity of reference and alternate sequence embeddings) 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-Ps on GFMBench-API BRCA1 (zs-embedding) lit-genomics-20261011-gfmbench-protocol-brca1-zs-embedding Aggregation: Not reported GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models · Table 3, task 'BRCA1', row 'Caduceus-Ps', column 'Cos AUPRC'
Configuration: Caduceus-Ps (zero-shot, GFMBench-API)	Protocol: GFMBench-API BRCA1, zs-embedding Dataset: BRCA1 test set (GFMBench-API)	0.555 AUROC (zero-shot; cosine similarity of reference and alternate sequence embeddings) 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-Ps on GFMBench-API BRCA1 (zs-embedding) lit-genomics-20261011-gfmbench-protocol-brca1-zs-embedding Aggregation: Not reported GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models · Table 3, task 'BRCA1', row 'Caduceus-Ps', column 'Cos AUROC'
Configuration: Caduceus-Ps (zero-shot, GFMBench-API)	Protocol: GFMBench-API BRCA1, zs-embedding Dataset: BRCA1 test set (GFMBench-API)	0.299 AUPRC (zero-shot; L2 distance of reference and alternate sequence embeddings) 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-Ps on GFMBench-API BRCA1 (zs-embedding) lit-genomics-20261011-gfmbench-protocol-brca1-zs-embedding Aggregation: Not reported GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models · Table 3, task 'BRCA1', row 'Caduceus-Ps', column 'L2 AUPRC'
Configuration: Caduceus-Ps (zero-shot, GFMBench-API)	Protocol: GFMBench-API BRCA1, zs-embedding Dataset: BRCA1 test set (GFMBench-API)	0.563 AUROC (zero-shot; L2 distance of reference and alternate sequence embeddings) 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-Ps on GFMBench-API BRCA1 (zs-embedding) lit-genomics-20261011-gfmbench-protocol-brca1-zs-embedding Aggregation: Not reported GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models · Table 3, task 'BRCA1', row 'Caduceus-Ps', column 'L2 AUROC'
Configuration: Caduceus-Ps (zero-shot, GFMBench-API)	Protocol: GFMBench-API BRCA1, zs-embedding Dataset: BRCA1 test set (GFMBench-API)	0.203 AUPRC (zero-shot; cosine similarity of embeddings at the SNV position) 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-Ps on GFMBench-API BRCA1 (zs-embedding) lit-genomics-20261011-gfmbench-protocol-brca1-zs-embedding Aggregation: Not reported GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models · Table 3, task 'BRCA1', row 'Caduceus-Ps', column 'SNV Cos AUPRC'
Configuration: Caduceus-Ps (zero-shot, GFMBench-API)	Protocol: GFMBench-API BRCA1, zs-embedding Dataset: BRCA1 test set (GFMBench-API)	0.469 AUROC (zero-shot; cosine similarity of embeddings at the SNV position) 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-Ps on GFMBench-API BRCA1 (zs-embedding) lit-genomics-20261011-gfmbench-protocol-brca1-zs-embedding Aggregation: Not reported GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models · Table 3, task 'BRCA1', row 'Caduceus-Ps', column 'SNV Cos AUROC'
Configuration: Caduceus-Ps (zero-shot, GFMBench-API)	Protocol: GFMBench-API BRCA1, zs-mlm-llr Dataset: BRCA1 test set (GFMBench-API)	0.218 AUPRC (zero-shot; masked log-likelihood ratio) 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-Ps on GFMBench-API BRCA1 (zs-mlm-llr) lit-genomics-20261011-gfmbench-protocol-brca1-zs-mlm-llr Aggregation: Not reported GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models · Table 4, task 'BRCA1', row 'Caduceus-Ps', column 'Msk LLR PRC'
Configuration: Caduceus-Ps (zero-shot, GFMBench-API)	Protocol: GFMBench-API BRCA1, zs-mlm-llr Dataset: BRCA1 test set (GFMBench-API)	0.483 AUROC (zero-shot; masked log-likelihood ratio) 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-Ps on GFMBench-API BRCA1 (zs-mlm-llr) lit-genomics-20261011-gfmbench-protocol-brca1-zs-mlm-llr Aggregation: Not reported GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models · Table 4, task 'BRCA1', row 'Caduceus-Ps', column 'Msk LLR ROC'
Configuration: Caduceus-Ps (zero-shot, GFMBench-API)	Protocol: GFMBench-API ClinVar Indel Pathogenicity, zs-embedding Dataset: ClinVar Indel Pathogenicity test set (GFMBench-API)	0.958 AUPRC (zero-shot; cosine similarity of reference and alternate sequence embeddings) 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-Ps on GFMBench-API ClinVar Indel Pathogenicity (zs-embedding) lit-genomics-20261011-gfmbench-protocol-clinvar-indel-pathogenicity-zs-embedding Aggregation: Not reported GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models · Table 3, task 'ClinVar Indel Pathogenicity', row 'Caduceus-Ps', column 'Cos AUPRC'

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

GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models · Original source · bioRxiv preprint version 2, posted 2026-08-11

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: lit-genomics-20261011-gfmbench-config-caduceus-ps-zero-shot

areas: dna-genomes
contexts: research
method types: foundation_model
reported name: Caduceus-Ps
foundation model eligible: true
parameters: About 7M parameters; Hugging Face checkpoint; zero-shot
access reuse: Public checkpoint (Hugging Face; Evo2 via NVIDIA BioNeMo)
source locator: Benchmark Results sections A and B
missing metadata: version: reason: unreported; note: Checkpoint revision not printed; parameter count only
provenance note: Caduceus-Ps as evaluated in GFMBench-API, zero-shot.

Related records

Suggest a correction