Benchmark Catalog
126 individually catalogued benchmarks with 7-criterion composite scoring and experimental validation tier. Filter, sort, compare up to 4 side-by-side.
| ☐ | Name | Stages | Modalities | Validation | Score | Flags | Updated |
|---|---|---|---|---|---|---|---|
| Open Targets Platform | Disease ModelingTarget ID | cross-modality | Wet-lab confirmed | 100.0 | 2025-06 | ||
| DepMap (Cancer Dependency Map) | Target IDDisease Modeling | cross-modality | Wet-lab confirmed | 100.0 | 2025-06 | ||
| TDC ADMET Group | Lead ID / ADMET | small-molecule | Retrospective | 100.0 | 2025-04 | ||
| SAbDab | Hit IDLead ID / ADMETDevelopmental Candidate | biologic-mab | Retrospective | 100.0 | 2025-04 | ||
| Protein Language Model Eval 2026 | Virtual CellHit ID | biologic | Wet-lab confirmed | 100.0 | 2026-04 | ||
| ChEMBL | Hit IDLead ID / ADMET | small-moleculeprotein-general | Wet-lab confirmed | 97.5 | 2025-05 | ||
| Observed Antibody Space (OAS) | Hit IDLead ID / ADMET | biologic-mab | Retrospective | 97.5 | 2025-04 | ||
| ProteinGym | Target IDLead ID / ADMETIND-enabling | protein-general | Wet-lab confirmed | 97.5 | 2025-03 | ||
| CAFA 6 (Critical Assessment of Function Annotation 6) | Target ID | protein_sequence | Wet-lab confirmed | 97.5 | competitionkaggletime_delayed_evaluation | 2026-05 | |
| PoseBusters | Hit ID | small-moleculeprotein-general | Retrospective | 97.0 | 2025-02 | ||
| PLINDER | Hit ID | small-moleculeprotein-general | Retrospective | 97.0 | 2025-03 | ||
| Virtual Cell Benchmark Suite 2026 | Virtual Cell | cross-modality | Prospective | 97.0 | 2026-04 | ||
| PLINDER v2 Protein-Ligand Benchmark | Hit ID | small-moleculebiologic | Retrospective | 97.0 | 2026-03 | ||
| Therapeutic Antibody Design Benchmark 2026 | Hit IDLead ID / ADMET | biologic | Wet-lab confirmed | 97.0 | 2026-04 | ||
| Protein Design Benchmark 2026 | Hit ID | biologic | Wet-lab confirmed | 97.0 | 2026-04 | ||
| STRING | Target IDDisease Modeling | protein-general | Retrospective | 94.9 | 2024-11 | ||
| CASP15 | Hit IDTarget ID | protein-general | Retrospective | 94.9 | 2023 | ||
| RxRx3 Phenomics Benchmark | Hit IDLead ID / ADMET | small-molecule | Wet-lab confirmed | 94.9 | 2026-03 | ||
| CASP16 | Hit ID | protein-generalsmall-molecule | Retrospective | 94.4 | 2024-12 | ||
| CAMEO weekly targets | Hit ID | protein-generalsmall-molecule | Retrospective | 94.4 | 2025-05 | ||
| Boltz-1 Structure Prediction Benchmark | Hit ID | biologicsmall-molecule | Retrospective | 94.4 | 2026-02 | ||
| X-Atlas/Pisces (25.6M Cell Multi-Context Perturb-seq) | Target ID | genetic_perturbationsingle_cell | Wet-lab confirmed | 94.4 | foundation_model_dataindustry_generatedlargest_in_class | 2026-03 | |
| ORD Reaction Benchmark | Developmental Candidate | small-molecule | Retrospective | 93.9 | 2025-04 | ||
| ASAP Discovery Antiviral 2025 | Hit IDLead ID / ADMET | small-molecule | Prospective | 93.9 | 2026-02 | ||
| Open Problems: Perturbation Prediction | Virtual Cell | cross-modality | Retrospective | 91.9 | 2024-12 | ||
| PrimeKG | Disease ModelingTarget ID | cross-modality | Retrospective | 91.9 | 2025-02 | ||
| FLAb2 (Fitness Landscape for Antibodies 2) | IND-enablingLead ID / ADMET | antibodyprotein_sequence | Wet-lab confirmed | 91.9 | biologicsmulti_property | 2025-12 | |
| scPerturBench | Target ID | chemical_perturbationgenetic_perturbationsingle_cell | Retrospective | 91.9 | nature_methodscomprehensive_comparison | 2025-12 | |
| X-Atlas/Orion (Xaira Genome-wide Perturb-seq) | Target ID | genetic_perturbationsingle_cell | Wet-lab confirmed | 91.4 | foundation_model_dataindustry_generated | 2025-06 | |
| PoseX (Protein-Ligand Docking Benchmark) | Hit IDLead ID / ADMET | protein_structuresmall-molecule | Retrospective | 91.4 | leakage_preventioncross_dockingleaderboard | 2025-12 | |
| FAERS (raw) | Post-market / RWE | small-moleculebiologic-mab | Retrospective | 91.1 | 2025-Q2 | ||
| Longevity Benchmark (Insilico) | Disease ModelingTarget IDPost-market / RWE | cross-modality | Prospective | 90.6 | 2026-04 | ||
| LINCS L1000 / CMap | Virtual CellDisease ModelingTarget ID | small-moleculecross-modality | Wet-lab confirmed | 89.9 | 2024-03 | ||
| canSAR | Target IDHit ID | small-moleculeprotein-general | Wet-lab confirmed | 89.4 | 2024-09 | ||
| MIMIC-IV Benchmark Tasks | phase-iiiClinical DevelopmentPost-market / RWE | cross-modality | Clinical | 89.4 | 2025-02 | ||
| scPerturb | Virtual CellTarget ID | cross-modality | Retrospective | 88.9 | 2024-11 | ||
| PINDER | Hit ID | protein-general | Retrospective | 88.9 | 2025-03 | ||
| Practical Molecular Optimization (PMO) | Lead ID / ADMETDevelopmental Candidate | small-molecule | Retrospective | 88.9 | 2024-10 | ||
| CoV-AbDab | Hit ID | biologic-mab | Retrospective | 88.9 | 2024-12 | ||
| NucleoBench | Hit IDLead ID / ADMET | dnarnanucleic_acid | Retrospective | 88.9 | gene_therapyrna_therapeuticsgoogle_research | 2025-09 | |
| PubChem BioAssay | Hit ID | small-molecule | Wet-lab confirmed | 88.6 | 2025-05 | ||
| Polaris ADMET | Lead ID / ADMET | small-molecule | Prospective | 88.4 | 2025-04 | ||
| BenchBB (Bench-tested Binder Benchmark) | Hit IDLead ID / ADMET | protein_structureprotein_sequence | Wet-lab confirmed | 88.4 | experimental_validationcompetitionwet_lab | 2025-10 | |
| CZ Virtual Cell Challenge | Virtual CellTarget ID | cross-modality | Prospective | 88.1 | 2025-09 | ||
| Cell Line Sensitivity Benchmark (CLSB) | Target IDLead ID / ADMET | small-molecule | Wet-lab confirmed | 88.1 | 2026-03 | ||
| ISM Benchmarks: GPCRs (Insilico) | Hit IDLead ID / ADMET | small-moleculeprotein-general | Retrospective | 87.6 | 2026-04 | ||
| ClinBench Quarterly — Q2 2026 | phase-iiphase-iiiClinical Development | cross-modality | Clinical | 87.6 | 2026-04 | ||
| CAPRI Rounds | Hit ID | protein-general | Retrospective | 86.3 | 2024-11 | ||
| mRNABench (mRNA Property Prediction Benchmark) | Hit IDLead ID / ADMET | rnanucleic_acid | Retrospective | 86.3 | rna_therapeuticsfoundation_model_eval | 2025-07 | |
| ToxCast | Lead ID / ADMETIND-enabling | small-molecule | Retrospective | 85.6 | 2024-06 | ||
| GNNBench-Drug 2026 | Hit IDLead ID / ADMET | small-molecule | Retrospective | 85.6 | 2026-03 | ||
| OpenBind EV-A71 Structure-Affinity Dataset | Hit IDLead ID / ADMET | protein_structuresmall-molecule | Wet-lab confirmed | 84.8 | experimental_validationcrystallography | 2026-05 | |
| CT-Open (Live Clinical Trial Outcome Benchmark) | phase-iiiphase-iphase-ii | small-moleculetextclinical_data | Retrospective | 84.8 | live_benchmarkleakage_freeclinical | 2026-05 | |
| TargetBench (Insilico) | Target IDDisease Modeling | cross-modality | Wet-lab confirmed | 84.6 | 2026-04 | ||
| ISM Benchmarks: ADMET (Insilico) | Lead ID / ADMETIND-enabling | small-molecule | Wet-lab confirmed | 84.6 | 2026-04 | ||
| Longevity Compound Benchmark | Hit IDLead ID / ADMET | small-molecule | Wet-lab confirmed | 84.6 | 2026-04 | ||
| CAFA5 | Target ID | protein-general | Retrospective | 84.3 | 2023-12 | ||
| DMPKBench (DMPK LLM Evaluation Benchmark) | IND-enablingLead ID / ADMET | texttabularsmall-molecule | None | 83.8 | llm_benchmarkmulti_modalchinese_benchmark | 2025-12 | |
| MoleculeACE | Lead ID / ADMET | small-molecule | Retrospective | 83.3 | 2024-05 | ||
| MatBench | Developmental Candidate | cross-modality | Retrospective | 83.3 | 2025-02 | ||
| BOOM (Benchmarking Out-Of-Distribution Molecular Predictions) | Hit IDLead ID / ADMET | small-molecule | None | 83.3 | neurips_2025ood_evaluationcritical_finding | 2025-12 | |
| OffSides / TWOSIDES | Post-market / RWE | small-molecule | Retrospective | 83.0 | 2023-09 | ||
| DrugComb 2.0 Synergy Benchmark | Lead ID / ADMETDevelopmental Candidate | small-molecule | Retrospective | 83.0 | 2026-03 | ||
| DMPK Integrated Benchmark | Lead ID / ADMETDevelopmental Candidate | small-molecule | Retrospective | 82.5 | 2026-02 | ||
| LSD Large-Scale Docking Database | Hit ID | protein_structuresmall-molecule | Wet-lab confirmed | 82.5 | ultra_large_scaleexperimental_validation | 2025-04 | |
| BELKA (Big Encoded Library for Chemical Assessment) | Hit ID | dna_encoded_librarysmall-molecule | Retrospective | 82.5 | neurips_2024kaggleultra_large_scalecompetition | 2024-10 | |
| CycPeptMPDB (Cyclic Peptide Membrane Permeability Database) | IND-enablingLead ID / ADMET | peptide | Wet-lab confirmed | 82.5 | biologicspeptide_therapeuticspermeability | 2024-12 | |
| mRNA Design Benchmark (CodonBench 2026) | Hit IDLead ID / ADMET | rna-therapeutic | Prospective | 82.0 | 2026-04 | ||
| ClinBench Quarterly (Insilico) | phase-iiphase-iiiClinical Development | cross-modality | Clinical | 81.5 | 2026-04 | ||
| DOCKSTRING | Hit ID | small-molecule | Retrospective | 81.3 | 2024-07 | ||
| DisGeNET | Disease ModelingTarget ID | cross-modality | Retrospective | 81.0 | license-gated-commercial | 2024-11 | |
| LIT-PCBA | Hit ID | small-molecule | Retrospective | 80.8 | 2023-06 | ||
| FLIP | Target IDDevelopmental Candidate | protein-general | Retrospective | 80.8 | 2024-05 | ||
| CPTAC Proteogenomic Benchmarks | Disease ModelingTarget IDphase-ii | cross-modality | Clinical | 80.8 | 2025-03 | ||
| AbBiBench (Antibody Binding Benchmark) | Lead ID / ADMET | protein_structureantibody | Retrospective | 80.8 | biologicsaffinity_maturation | 2025-10 | |
| GuacaMol | Lead ID / ADMETDevelopmental Candidate | small-molecule | Retrospective | 80.5 | 2022-07 | ||
| Open Systems Pharmacology / PK-Sim | phase-iIND-enabling | small-moleculebiologic-mab | Retrospective | 80.3 | 2025-01 | ||
| pepADMET | IND-enablingLead ID / ADMET | peptidesmall-molecule | Retrospective | 80.0 | biologicspeptide_therapeuticsfirst_in_class | 2026-01 | |
| ADMET-AI | Lead ID / ADMET | small-molecule | Retrospective | 79.5 | 2024-12 | ||
| AMES (mutagenicity) | IND-enablingLead ID / ADMET | small-molecule | Retrospective | 79.5 | 2025-01 | ||
| scImmuneBench | Virtual CellDisease Modeling | cell-therapy | Retrospective | 79.5 | 2026-03 | ||
| CRISPR Outcome Prediction Benchmark | Hit ID | gene-therapy | Wet-lab confirmed | 79.5 | 2026-02 | ||
| Polaris Biologics (Polyreactivity / SEC / Tm) | Developmental Candidate | biologic-mab | Prospective | 79.0 | 2025-03 | ||
| MolGenBench | Hit IDLead ID / ADMET | small-molecule | Retrospective | 78.2 | hit_to_leadreal_world_metrics | 2025-11 | |
| MoleculeNet | Lead ID / ADMETHit ID | small-molecule | Retrospective | 78.0 | data-leakage-known | 2023-11 | |
| USPTO-50K / USPTO-MIT (Retrosynthesis) | Lead ID / ADMETDevelopmental Candidate | small-molecule | Retrospective | 78.0 | data-leakage-known | 2023 | |
| BioDesignBench | Hit IDLead ID / ADMET | protein_structureai_agentprotein_sequence | Retrospective | 77.7 | agent_benchmarkprotein_engineering | 2026-05 | |
| Tox21 | Lead ID / ADMETIND-enabling | small-molecule | Retrospective | 77.5 | 2017 | ||
| IgLM / AntiBERTa benchmarks | Hit IDDevelopmental Candidate | biologic-mab | Wet-lab confirmed | 77.5 | 2024-08 | ||
| Geneformer Eval | Virtual Cell | cross-modality | Wet-lab confirmed | 77.0 | self_referential | 2024-11 | |
| TDC DrugSyn (OncoPolyPharm + DrugComb_NCI60) | Developmental CandidateLead ID / ADMET | small-molecule | Wet-lab confirmed | 77.0 | 2024-12 | ||
| Obach PK Dataset | phase-iIND-enablingLead ID / ADMET | small-molecule | Retrospective | 77.0 | 2024-06 | ||
| FGBench (Functional Group Molecular Property Reasoning) | Hit IDLead ID / ADMET | textsmall-molecule | None | 77.0 | neurips_2025llm_benchmarkinterpretability | 2026-04 | |
| HINT / TrialBench | phase-iiphase-iiiClinical Development | cross-modality | Clinical | 76.5 | 2024-07 | ||
| Trial Outcome Prediction (TOP) | phase-iiiClinical Development | cross-modality | Clinical | 76.5 | 2024 | ||
| CASF-2016 | Hit ID | small-moleculeprotein-general | Retrospective | 76.2 | 2019 | ||
| PDBbind | Hit IDLead ID / ADMET | small-moleculeprotein-general | Retrospective | 75.9 | data-leakage-known | 2022-01 | |
| SIDER | Post-market / RWEIND-enabling | small-molecule | Retrospective | 74.9 | 2016 | ||
| TAPE | Target IDDevelopmental Candidate | protein-general | Retrospective | 74.9 | deprecated-recommend-replace | 2022 | |
| Simcyp Validation Sets | phase-iphase-iiIND-enabling | small-molecule | Retrospective | 74.4 | license-gated-commercial | 2024 | |
| PEER | Target IDDevelopmental Candidate | protein-general | Retrospective | 74.4 | 2024 | ||
| PerturbArena | Target ID | chemical_perturbationgenetic_perturbationsingle_cell | None | 74.4 | virtual_cellmulti_metric | 2025-06 | |
| ClawBio Skill Correctness Bench | Disease ModelingTarget IDClinical Development | cross-modality | Retrospective | 74.2 | 2026-05-03 | ||
| hERG (cardio-tox) TDC | IND-enablingLead ID / ADMET | small-molecule | Retrospective | 73.9 | 2025-01 | ||
| DILI / LD50 Zhu | IND-enablingLead ID / ADMET | small-molecule | Retrospective | 73.9 | 2024-12 | ||
| scGPT Evaluation Suite | Virtual Cell | cross-modality | Wet-lab confirmed | 73.7 | self_referential | 2025-01 | |
| CT-Outcome (TrialBench v2) | phase-iiphase-iii | cross-modality | Clinical | 73.4 | 2025-03 | ||
| DUD-E | Hit ID | small-molecule | Retrospective | 72.9 | data-leakage-knowndeprecated-recommend-replace | 2014 | |
| MOSES | Lead ID / ADMETDevelopmental Candidate | small-molecule | Retrospective | 72.4 | 2022-04 | ||
| AWS-JHU Antibody Developability Benchmark | Developmental CandidateLead ID / ADMET | biologic | Wet-lab confirmed | 72.3 | 2026-04-14 | ||
| PerturbBench | Virtual Cell | cross-modality | Retrospective | 71.4 | 2025-06 | ||
| DO Challenge 2025 (DeepOrigin Autonomous Drug Discovery) | Hit ID | ai_agentsmall-molecule | None | 70.9 | competitionagent_benchmark | 2025-05 | |
| ScaleBench: Molecular Property Prediction | Lead ID / ADMETHit ID | small-molecule | Retrospective | 69.5 | 2026-05-15 | ||
| PDFBench (De Novo Protein Design from Function) | Hit ID | protein_structuretextprotein_sequence | None | 68.9 | text_guided_designmulti_metric | 2025-05 | |
| DrugPlayGround | Hit IDTarget IDLead ID / ADMET | small-molecule | Retrospective | 66.8 | 2026-04-07 | ||
| VSDS-vd (Virtual Screening Decoy Set for Docking) | Hit ID | protein_structuresmall-molecule | None | 65.8 | chinese_benchmarkvirtual_screening | 2025-02 | |
| ClinTox | Lead ID / ADMETIND-enabling | small-molecule | Retrospective | 65.6 | data-leakage-known | 2022 | |
| CellBench-LS | Virtual CellDisease Modeling | small-moleculebiologic | Retrospective | 65.2 | 2026-04-01 | ||
| AssayBench | Target IDHit ID | textgenetic_perturbationsingle_cell | None | 63.3 | virtual_cellllm_benchmarkphenotypic | 2026-05 | |
| DEKOIS 2.0 | Hit ID | small-molecule | Retrospective | 57.5 | deprecated-recommend-replace | 2019 | |
| FoldBench | Hit ID | small moleculebiologic | Retrospective | 55.8 | 2026-03-15 | ||
| OpenADMET / Avoid-ome | Lead ID / ADMETIND-enabling | small molecule | Retrospective | 53.6 | 2026-05-25 | ||
| SAIR | Hit ID | small molecule | Retrospective | 51.2 | self_referential | 2026-04-25 | |
| MPP Foundation Model Benchmark | Lead ID / ADMETHit ID | small molecule | Retrospective | 50.3 | 2026-04-17 | ||
| VibeProteinBench (VPD-Bench) | Target IDDevelopmental Candidate | biologicsmall molecule | None | 43.2 | 2026-05-18 | ||
| CompGen-MLIP: Compositional Generalisation for ML Interatomic Potentials | Hit IDLead ID / ADMET | small molecule | Retrospective | 39.8 | 2026-05-09 |