| GFMBench-API Bend Variant Effects Disease, zs-embedding | Bend Variant Effects Disease test set (GFMBench-API) | AUPRC (zero-shot; L2 distance of reference and alternate sequence embeddings), unitless | 0.596 | 0.379 | Evo 2 |
| GFMBench-API Bend Variant Effects Disease, zs-embedding | Bend Variant Effects Disease test set (GFMBench-API) | AUPRC (zero-shot; cosine similarity of embeddings at the SNV position), unitless | 0.0944 | 0.107 | Caduceus |
| GFMBench-API Bend Variant Effects Disease, zs-embedding | Bend Variant Effects Disease test set (GFMBench-API) | AUPRC (zero-shot; cosine similarity of reference and alternate sequence embeddings), unitless | 0.474 | 0.378 | Evo 2 |
| GFMBench-API Bend Variant Effects Disease, zs-embedding | Bend Variant Effects Disease test set (GFMBench-API) | AUROC (zero-shot; L2 distance of reference and alternate sequence embeddings), unitless | 0.912 | 0.78 | Evo 2 |
| GFMBench-API Bend Variant Effects Disease, zs-embedding | Bend Variant Effects Disease test set (GFMBench-API) | AUROC (zero-shot; cosine similarity of embeddings at the SNV position), unitless | 0.615 | 0.545 | Evo 2 |
| GFMBench-API Bend Variant Effects Disease, zs-embedding | Bend Variant Effects Disease test set (GFMBench-API) | AUROC (zero-shot; cosine similarity of reference and alternate sequence embeddings), unitless | 0.872 | 0.772 | Evo 2 |
| GFMBench-API Bend Variant Effects Expression, zs-embedding | Bend Variant Effects Expression test set (GFMBench-API) | AUPRC (zero-shot; L2 distance of reference and alternate sequence embeddings), unitless | 0.0897 | 0.0692 | Evo 2 |
| GFMBench-API Bend Variant Effects Expression, zs-embedding | Bend Variant Effects Expression test set (GFMBench-API) | AUPRC (zero-shot; cosine similarity of embeddings at the SNV position), unitless | 0.0887 | 0.0775 | Evo 2 |
| GFMBench-API Bend Variant Effects Expression, zs-embedding | Bend Variant Effects Expression test set (GFMBench-API) | AUPRC (zero-shot; cosine similarity of reference and alternate sequence embeddings), unitless | 0.0904 | 0.0676 | Evo 2 |
| GFMBench-API Bend Variant Effects Expression, zs-embedding | Bend Variant Effects Expression test set (GFMBench-API) | AUROC (zero-shot; L2 distance of reference and alternate sequence embeddings), unitless | 0.573 | 0.479 | Evo 2 |
| GFMBench-API Bend Variant Effects Expression, zs-embedding | Bend Variant Effects Expression test set (GFMBench-API) | AUROC (zero-shot; cosine similarity of embeddings at the SNV position), unitless | 0.557 | 0.537 | Evo 2 |
| GFMBench-API Bend Variant Effects Expression, zs-embedding | Bend Variant Effects Expression test set (GFMBench-API) | AUROC (zero-shot; cosine similarity of reference and alternate sequence embeddings), unitless | 0.582 | 0.473 | Evo 2 |
| GFMBench-API BRCA1, zs-embedding | BRCA1 test set (GFMBench-API) | AUPRC (zero-shot; L2 distance of reference and alternate sequence embeddings), unitless | 0.575 | 0.299 | Evo 2 |
| GFMBench-API BRCA1, zs-embedding | BRCA1 test set (GFMBench-API) | AUPRC (zero-shot; cosine similarity of embeddings at the SNV position), unitless | 0.204 | 0.203 | Tie |
| GFMBench-API BRCA1, zs-embedding | BRCA1 test set (GFMBench-API) | AUPRC (zero-shot; cosine similarity of reference and alternate sequence embeddings), unitless | 0.54 | 0.291 | Evo 2 |
| GFMBench-API BRCA1, zs-embedding | BRCA1 test set (GFMBench-API) | AUROC (zero-shot; L2 distance of reference and alternate sequence embeddings), unitless | 0.775 | 0.563 | Evo 2 |
| GFMBench-API BRCA1, zs-embedding | BRCA1 test set (GFMBench-API) | AUROC (zero-shot; cosine similarity of embeddings at the SNV position), unitless | 0.467 | 0.469 | Tie |
| GFMBench-API BRCA1, zs-embedding | BRCA1 test set (GFMBench-API) | AUROC (zero-shot; cosine similarity of reference and alternate sequence embeddings), unitless | 0.747 | 0.555 | Evo 2 |
| GFMBench-API ClinVar Indel Pathogenicity, zs-embedding | ClinVar Indel Pathogenicity test set (GFMBench-API) | AUPRC (zero-shot; L2 distance of reference and alternate sequence embeddings), unitless | 0.993 | 0.959 | Evo 2 |
| GFMBench-API ClinVar Indel Pathogenicity, zs-embedding | ClinVar Indel Pathogenicity test set (GFMBench-API) | AUPRC (zero-shot; cosine similarity of reference and alternate sequence embeddings), unitless | 0.989 | 0.958 | Evo 2 |
| GFMBench-API ClinVar Indel Pathogenicity, zs-embedding | ClinVar Indel Pathogenicity test set (GFMBench-API) | AUROC (zero-shot; L2 distance of reference and alternate sequence embeddings), unitless | 0.967 | 0.71 | Evo 2 |
| GFMBench-API ClinVar Indel Pathogenicity, zs-embedding | ClinVar Indel Pathogenicity test set (GFMBench-API) | AUROC (zero-shot; cosine similarity of reference and alternate sequence embeddings), unitless | 0.946 | 0.708 | Evo 2 |
| GFMBench-API LOL-EVE, zs-embedding | LOL-EVE test set (GFMBench-API) | AUPRC (zero-shot; L2 distance of reference and alternate sequence embeddings), unitless | 0.0938 | 0.0863 | Evo 2 |
| GFMBench-API LOL-EVE, zs-embedding | LOL-EVE test set (GFMBench-API) | AUPRC (zero-shot; cosine similarity of reference and alternate sequence embeddings), unitless | 0.0845 | 0.0861 | Caduceus |
| GFMBench-API LOL-EVE, zs-embedding | LOL-EVE test set (GFMBench-API) | AUROC (zero-shot; L2 distance of reference and alternate sequence embeddings), unitless | 0.543 | 0.522 | Evo 2 |
| GFMBench-API LOL-EVE, zs-embedding | LOL-EVE test set (GFMBench-API) | AUROC (zero-shot; cosine similarity of reference and alternate sequence embeddings), unitless | 0.531 | 0.524 | Evo 2 |
| GFMBench-API LRB Variant Effect OMIM, zs-embedding | LRB Variant Effect OMIM test set (GFMBench-API) | AUPRC (zero-shot; L2 distance of reference and alternate sequence embeddings), unitless | 0.0021 | 0.0019 | Evo 2 |
| GFMBench-API LRB Variant Effect OMIM, zs-embedding | LRB Variant Effect OMIM test set (GFMBench-API) | AUPRC (zero-shot; cosine similarity of embeddings at the SNV position), unitless | 0.002 | 0.0022 | Caduceus |
| GFMBench-API LRB Variant Effect OMIM, zs-embedding | LRB Variant Effect OMIM test set (GFMBench-API) | AUPRC (zero-shot; cosine similarity of reference and alternate sequence embeddings), unitless | 0.002 | 0.0019 | Evo 2 |
| GFMBench-API LRB Variant Effect OMIM, zs-embedding | LRB Variant Effect OMIM test set (GFMBench-API) | AUROC (zero-shot; L2 distance of reference and alternate sequence embeddings), unitless | 0.502 | 0.49 | Evo 2 |
| GFMBench-API LRB Variant Effect OMIM, zs-embedding | LRB Variant Effect OMIM test set (GFMBench-API) | AUROC (zero-shot; cosine similarity of embeddings at the SNV position), unitless | 0.498 | 0.524 | Caduceus |
| GFMBench-API LRB Variant Effect OMIM, zs-embedding | LRB Variant Effect OMIM test set (GFMBench-API) | AUROC (zero-shot; cosine similarity of reference and alternate sequence embeddings), unitless | 0.501 | 0.486 | Evo 2 |
| GFMBench-API Songlab ClinVar, zs-embedding | Songlab ClinVar test set (GFMBench-API) | AUPRC (zero-shot; L2 distance of reference and alternate sequence embeddings), unitless | 0.865 | 0.991 | Caduceus |
| GFMBench-API Songlab ClinVar, zs-embedding | Songlab ClinVar test set (GFMBench-API) | AUPRC (zero-shot; cosine similarity of embeddings at the SNV position), unitless | 0.576 | 0.991 | Caduceus |
| GFMBench-API Songlab ClinVar, zs-embedding | Songlab ClinVar test set (GFMBench-API) | AUPRC (zero-shot; cosine similarity of reference and alternate sequence embeddings), unitless | 0.734 | 0.996 | Caduceus |
| GFMBench-API Songlab ClinVar, zs-embedding | Songlab ClinVar test set (GFMBench-API) | AUROC (zero-shot; L2 distance of reference and alternate sequence embeddings), unitless | 0.845 | 0.867 | Caduceus |
| GFMBench-API Songlab ClinVar, zs-embedding | Songlab ClinVar test set (GFMBench-API) | AUROC (zero-shot; cosine similarity of embeddings at the SNV position), unitless | 0.579 | 0.867 | Caduceus |
| GFMBench-API Songlab ClinVar, zs-embedding | Songlab ClinVar test set (GFMBench-API) | AUROC (zero-shot; cosine similarity of reference and alternate sequence embeddings), unitless | 0.722 | 0.933 | Caduceus |
| GFMBench-API TraitGym Complex, zs-embedding | TraitGym Complex test set (GFMBench-API) | AUPRC (zero-shot; L2 distance of reference and alternate sequence embeddings), unitless | 0.107 | 0.0974 | Evo 2 |
| GFMBench-API TraitGym Complex, zs-embedding | TraitGym Complex test set (GFMBench-API) | AUPRC (zero-shot; cosine similarity of embeddings at the SNV position), unitless | 0.106 | 0.103 | Evo 2 |
| GFMBench-API TraitGym Complex, zs-embedding | TraitGym Complex test set (GFMBench-API) | AUPRC (zero-shot; cosine similarity of reference and alternate sequence embeddings), unitless | 0.108 | 0.0946 | Evo 2 |
| GFMBench-API TraitGym Complex, zs-embedding | TraitGym Complex test set (GFMBench-API) | AUROC (zero-shot; L2 distance of reference and alternate sequence embeddings), unitless | 0.524 | 0.497 | Evo 2 |
| GFMBench-API TraitGym Complex, zs-embedding | TraitGym Complex test set (GFMBench-API) | AUROC (zero-shot; cosine similarity of embeddings at the SNV position), unitless | 0.523 | 0.518 | Tie |
| GFMBench-API TraitGym Complex, zs-embedding | TraitGym Complex test set (GFMBench-API) | AUROC (zero-shot; cosine similarity of reference and alternate sequence embeddings), unitless | 0.527 | 0.483 | Evo 2 |
| GFMBench-API TraitGym Mendelian, zs-embedding | TraitGym Mendelian test set (GFMBench-API) | AUPRC (zero-shot; L2 distance of reference and alternate sequence embeddings), unitless | 0.17 | 0.0922 | Evo 2 |
| GFMBench-API TraitGym Mendelian, zs-embedding | TraitGym Mendelian test set (GFMBench-API) | AUPRC (zero-shot; cosine similarity of embeddings at the SNV position), unitless | 0.121 | 0.127 | Caduceus |
| GFMBench-API TraitGym Mendelian, zs-embedding | TraitGym Mendelian test set (GFMBench-API) | AUPRC (zero-shot; cosine similarity of reference and alternate sequence embeddings), unitless | 0.164 | 0.0879 | Evo 2 |
| GFMBench-API TraitGym Mendelian, zs-embedding | TraitGym Mendelian test set (GFMBench-API) | AUROC (zero-shot; L2 distance of reference and alternate sequence embeddings), unitless | 0.626 | 0.477 | Evo 2 |
| GFMBench-API TraitGym Mendelian, zs-embedding | TraitGym Mendelian test set (GFMBench-API) | AUROC (zero-shot; cosine similarity of embeddings at the SNV position), unitless | 0.548 | 0.553 | Tie |
| GFMBench-API TraitGym Mendelian, zs-embedding | TraitGym Mendelian test set (GFMBench-API) | AUROC (zero-shot; cosine similarity of reference and alternate sequence embeddings), unitless | 0.618 | 0.463 | Evo 2 |