{
 "as_of": "2026-11-16",
 "note": "Scores are verbatim and not comparable across benchmarks.",
 "rows": [
  {
   "nn": "01",
   "benchmark": "CASP",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/casp/",
   "domain": "Structure & co-folding",
   "type": "A",
   "evidence_level": "L4",
   "first_release": "1994",
   "latest_update": "2026-09-11, new round",
   "status": "Active",
   "wetlab_refresh": "New",
   "models_reported": 15,
   "ranking_status": "No ranking",
   "current_ranking": "No ranking: CASP has no single overall board and CASP17 results are not out yet."
  },
  {
   "nn": "05",
   "benchmark": "PoseBusters",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/posebusters/",
   "domain": "Structure & co-folding",
   "type": "C+B",
   "evidence_level": "L3",
   "first_release": "2023-08-10",
   "latest_update": "2026-10-03, maintenance only",
   "status": "Active",
   "wetlab_refresh": "Static",
   "models_reported": 8,
   "ranking_status": "Not comparable",
   "current_ranking": "Not comparable: 5 results on different protocols, no single ranking"
  },
  {
   "nn": "15",
   "benchmark": "CAMEO",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/cameo/",
   "domain": "Structure & co-folding",
   "type": "A",
   "evidence_level": "L4",
   "first_release": "2012 (partly verified)",
   "latest_update": "no sourced date, no later event",
   "status": "Active",
   "wetlab_refresh": "New",
   "models_reported": 4,
   "ranking_status": "Third-party",
   "current_ranking": "Third-party: No headline number: the ranking source has no rank-1 entry (entries are unranked or protocol-specific); the caveat text is shown instead."
  },
  {
   "nn": "22",
   "benchmark": "CAPRI",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/capri/",
   "domain": "Structure & co-folding",
   "type": "A",
   "evidence_level": "L4",
   "first_release": "2001 (partly verified)",
   "latest_update": "2026-11-02, new round",
   "status": "Round in progress",
   "wetlab_refresh": "New",
   "models_reported": 2,
   "ranking_status": "No ranking",
   "current_ranking": "No ranking: There is no ranking this round, and the entries come from the CASP16 assessment of the joint round rather than a CAPRI-own standing."
  },
  {
   "nn": "25",
   "benchmark": "RNA-Puzzles",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/rnapuzzles/",
   "domain": "Structure & co-folding",
   "type": "A+B",
   "evidence_level": "L2–L4",
   "first_release": "2012-02-23",
   "latest_update": "2026-04-02 (unverified), new round",
   "status": "Low-frequency",
   "wetlab_refresh": "New",
   "models_reported": 3,
   "ranking_status": "Board",
   "current_ranking": "Board: Kaggle private-board rank 1 team, 0.578 (all, n=20); 0.491 (RNA-Puzzles, n=10) (Mean TM-align (US-align, C1'); Kaggle Stanford RNA 3D Folding Part 1 private board: 20 targets incl. 10 RNA-Puzzles) · Board · 2025-12-30"
  },
  {
   "nn": "30",
   "benchmark": "PLINDER / PINDER / Runs N' Poses",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/plinder/",
   "domain": "Structure & co-folding",
   "type": "C+B",
   "evidence_level": "L3",
   "first_release": "2024-07-17 (partly verified)",
   "latest_update": "2026-10-09 (partly verified), new version",
   "status": "Active",
   "wetlab_refresh": "Accumulating",
   "models_reported": 5,
   "ranking_status": "Board",
   "current_ranking": "Board: AlphaFold3, success_rate 15.068; rmsd_success_rate 17.808; mean_lddt_pli 0.304; coverage 96.053 (success_rate: share of predictions with LDDT-PLI > 0.8 and BiSyRMSD < 2; the page also lists rmsd_success_rate, mean_lddt_pli and coverage; Runs N' Poses (Polaris preview benchmark, plinder-org/runs-n-poses)) · Board · 2026-11-16"
  },
  {
   "nn": "31",
   "benchmark": "FoldBench",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/foldbench/",
   "domain": "Structure & co-folding",
   "type": "B",
   "evidence_level": "L3",
   "first_release": "2025-05-27",
   "latest_update": "2025-12-31, board entry",
   "status": "Low-frequency",
   "wetlab_refresh": "Static",
   "models_reported": 12,
   "ranking_status": "Board",
   "current_ranking": "Board: AlphaFold 3, Protein-Protein 72.93% / Antibody-Antigen 47.90% / Protein-Ligand 64.90%; Protein-RNA 62.32%, Protein-DNA 79.18%, RNA Monomer 0.61, DNA Monomer 0.53 (Interface success rate (% ; DockQ>=0.23, protein-ligand requires LRMSD<2 A and LDDT-PLI>0.8); monomers use LDDT; FoldBench official repo leaderboard, full set (targets released after 2023-01)) · Board · 2026-11-16"
  },
  {
   "nn": "03",
   "benchmark": "MoleculeNet (+OGB)",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/moleculenet/",
   "domain": "Small molecules",
   "type": "B",
   "evidence_level": "L2–L3",
   "first_release": "2017-03-02",
   "latest_update": "2018-10-26, paper revision",
   "status": "Frozen",
   "wetlab_refresh": "Static",
   "models_reported": 2,
   "ranking_status": "Not comparable",
   "current_ranking": "Not comparable: 3 results on different protocols, no single ranking"
  },
  {
   "nn": "04",
   "benchmark": "TDC (ADMET + DTI)",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/tdc/",
   "domain": "Small molecules",
   "type": "B",
   "evidence_level": "L2–L3",
   "first_release": "2020-11-13",
   "latest_update": "2026-01-21, paper revision",
   "status": "Active",
   "wetlab_refresh": "Static",
   "models_reported": 4,
   "ranking_status": "Board",
   "current_ranking": "Board: None of the 22 official boards dates its entries, so every score is withheld and no entry can serve as headline."
  },
  {
   "nn": "06",
   "benchmark": "CASF-2016",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/casf/",
   "domain": "Small molecules",
   "type": "B",
   "evidence_level": "L2",
   "first_release": "2009-04-09",
   "latest_update": "2018-11-27, no later sourced event found (as of 2026-11-16)",
   "status": "Frozen",
   "wetlab_refresh": "Static",
   "models_reported": 0,
   "ranking_status": "Not comparable",
   "current_ranking": "Not comparable: 4 results on different protocols, no single ranking"
  },
  {
   "nn": "07",
   "benchmark": "USPTO family (+PaRoutes)",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/uspto/",
   "domain": "Small molecules",
   "type": "B",
   "evidence_level": "L2–L3",
   "first_release": "2014-02",
   "latest_update": "2022, data",
   "status": "Frozen",
   "wetlab_refresh": "Static",
   "models_reported": 5,
   "ranking_status": "Not comparable",
   "current_ranking": "Not comparable: 5 results on different protocols, no single ranking"
  },
  {
   "nn": "12",
   "benchmark": "DUD-E / LIT-PCBA",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/dude/",
   "domain": "Small molecules",
   "type": "B",
   "evidence_level": "L2",
   "first_release": "2012-07-05",
   "latest_update": "2025-02-05 (partly verified), maintenance only",
   "status": "Low-frequency",
   "wetlab_refresh": "Static",
   "models_reported": 2,
   "ranking_status": "Third-party",
   "current_ranking": "Third-party: No headline number: the ranking source gives no rank-1 entry (all entries are unranked or protocol-specific); the caveat text is shown instead, as for a not-comparable cell."
  },
  {
   "nn": "19",
   "benchmark": "PMO (Practical Molecular Optimization)",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/pmo/",
   "domain": "Small molecules",
   "type": "D",
   "evidence_level": "L2",
   "first_release": "2022-06-22",
   "latest_update": "2026-11-09 (partly verified), new version",
   "status": "Low-frequency",
   "wetlab_refresh": "Static",
   "models_reported": 2,
   "ranking_status": "Self-reported",
   "current_ranking": "Self-reported: GenMol, Sum 18.362 (Table 3, 'Goal-directed hit generation results', 23 PMO tasks, AUC top-10) (AUC top-10, summed over 23 oracles (max 23), 10,000-call budget; PMO 23 oracles (QED, DRD2, GSK3B, JNK3 plus 19 GuacaMol-derived), oracle functions via TDC) · Self-reported · 2025-01-10"
  },
  {
   "nn": "20",
   "benchmark": "CACHE",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/cache/",
   "domain": "Small molecules",
   "type": "A",
   "evidence_level": "L5",
   "first_release": "2021-12-01 (partly verified)",
   "latest_update": "2026-08 (partly verified), data",
   "status": "Active",
   "wetlab_refresh": "New",
   "models_reported": 0,
   "ranking_status": "No ranking",
   "current_ranking": "No ranking: The organizers publish no ranking and never name the models inside each workflow, so no number can serve as a headline."
  },
  {
   "nn": "27",
   "benchmark": "Polaris / ASAP / OpenADMET",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/polaris/",
   "domain": "Small molecules",
   "type": "A+C",
   "evidence_level": "L4",
   "first_release": "2023-11-23",
   "latest_update": "2025-06-06 (partly verified), new version",
   "status": "Low-frequency",
   "wetlab_refresh": "New",
   "models_reported": 0,
   "ranking_status": "No ranking",
   "current_ranking": "No ranking: Polaris-hosted boards are JS-rendered and unreadable, and the summary paper anonymises entries; the OpenADMET CYP board is outside this entry."
  },
  {
   "nn": "33",
   "benchmark": "PoseX",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/posex/",
   "domain": "Small molecules",
   "type": "B",
   "evidence_level": "L3",
   "first_release": "2025-05-03",
   "latest_update": "2026-04-26, paper revision",
   "status": "Active",
   "wetlab_refresh": "Static",
   "models_reported": 6,
   "ranking_status": "Third-party",
   "current_ranking": "Third-party: No headline number: the ranking source gives no rank-1 entry (all entries are unranked or protocol-specific); the caveat text is shown instead, as for a not-comparable cell."
  },
  {
   "nn": "44",
   "benchmark": "FS-Mol",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/fsmol/",
   "domain": "Small molecules",
   "type": "B",
   "evidence_level": "L3",
   "first_release": "2021-12",
   "latest_update": "2026-10-21 (partly verified), archived",
   "status": "Frozen",
   "wetlab_refresh": "Static",
   "models_reported": 0,
   "ranking_status": "Not comparable",
   "current_ranking": "Not comparable: 1 result on different protocols, no single ranking"
  },
  {
   "nn": "02",
   "benchmark": "ProteinGym",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/proteingym/",
   "domain": "Proteins",
   "type": "B",
   "evidence_level": "L2–L3",
   "first_release": "2022-05-27 (partly verified)",
   "latest_update": "2026-03-25 (partly verified), data",
   "status": "Low-frequency",
   "wetlab_refresh": "Accumulating",
   "models_reported": 10,
   "ranking_status": "Board",
   "current_ranking": "Board: AIDO Protein-RAG (16B), 0.518 (SE 0.0) (Average Spearman (zero-shot, DMS substitutions); ProteinGym v1.3, 217 substitution DMS assays, zero-shot) · Board · 2025-06-13"
  },
  {
   "nn": "17",
   "benchmark": "CAFA",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/cafa/",
   "domain": "Proteins",
   "type": "A",
   "evidence_level": "L4–L5",
   "first_release": "2010-09 (partly verified)",
   "latest_update": "2025-10-16 (unverified), new round",
   "status": "Active",
   "wetlab_refresh": "Accumulating",
   "models_reported": 0,
   "ranking_status": "No ranking",
   "current_ranking": "No ranking: CAFA6 final board and winners were not found; the only entry is an interim snapshot, so there is no headline number."
  },
  {
   "nn": "26",
   "benchmark": "FLIP / FLIP2",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/flip/",
   "domain": "Proteins",
   "type": "B",
   "evidence_level": "L2–L3",
   "first_release": "2021-11-11",
   "latest_update": "2026-04-23 (partly verified), new version",
   "status": "Low-frequency",
   "wetlab_refresh": "Static",
   "models_reported": 2,
   "ranking_status": "Not comparable",
   "current_ranking": "Not comparable: 3 results on different protocols, no single ranking"
  },
  {
   "nn": "28",
   "benchmark": "Adaptyv competitions / BenchBB",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/adaptyv/",
   "domain": "Proteins",
   "type": "A+B",
   "evidence_level": "L5",
   "first_release": "2024-07-18 (unverified)",
   "latest_update": "2026-10-26, new round",
   "status": "Active",
   "wetlab_refresh": "New",
   "models_reported": 4,
   "ranking_status": "No ranking",
   "current_ranking": "No ranking: The current round has no results and the organiser page shows no ranks or scores."
  },
  {
   "nn": "40",
   "benchmark": "MotifBench",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/motifbench/",
   "domain": "Proteins",
   "type": "D",
   "evidence_level": "L2",
   "first_release": "2025-02-18",
   "latest_update": "2026-11-13, board entry",
   "status": "Active",
   "wetlab_refresh": "Static",
   "models_reported": 3,
   "ranking_status": "Board",
   "current_ranking": "Board: RFD4-Proteina (indexed + medium thinking), 55.06 (± 1.35) (MotifBench score (0-100); 30 motif-scaffolding problems, official ProteinMPNN + ESMFold pipeline) · Board · 2026-11-16"
  },
  {
   "nn": "34",
   "benchmark": "AbBiBench",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/abbibench/",
   "domain": "Antibodies",
   "type": "B",
   "evidence_level": "L2–L3",
   "first_release": "2025-05-23",
   "latest_update": "2026-11-03, paper revision",
   "status": "Active",
   "wetlab_refresh": "Static",
   "models_reported": 6,
   "ranking_status": "Board",
   "current_ranking": "Board: ProteinMPNN, 0.29 (Approx. mean rho (header reads 'Approx. mean ρ² ↑'; page states values are two-decimal Spearman correlations from manuscript Figure 3a), each of 16 assays evaluated separately; AbBiBench manuscript-matched snapshot, 20 base methods / 23 implementations across 16 assays) · Board · 2026-10-19"
  },
  {
   "nn": "35",
   "benchmark": "FLAb / FLAb2",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/flab/",
   "domain": "Antibodies",
   "type": "B",
   "evidence_level": "L2–L3",
   "first_release": "2024-01-15",
   "latest_update": "2026-05-12, maintenance only",
   "status": "Active",
   "wetlab_refresh": "Accumulating",
   "models_reported": 1,
   "ranking_status": "Third-party",
   "current_ranking": "Third-party: The source has no rank-1 entry: values belong to different properties and settings, so only the caveat is shown."
  },
  {
   "nn": "36",
   "benchmark": "AIntibody",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/aintibody/",
   "domain": "Antibodies",
   "type": "A",
   "evidence_level": "L5",
   "first_release": "2024-11-04",
   "latest_update": "2026-08-19, data",
   "status": "Low-frequency",
   "wetlab_refresh": "New",
   "models_reported": 1,
   "ranking_status": "Board",
   "current_ranking": "Board: AuraIDE / AuraBind (Aureka Biotechnologies, internal model), KD 94.7 pM (KinExA); best experimental antibody 113 pM (Measured KD (HT-SPR and KinExA) plus five developability screens; placement per task; AIntibody round 1, 3 challenges, 511 designs from 29 organizations, SARS-CoV-2 spike RBD; all designs made and measured in one lab) · Board · 2026-08-19"
  },
  {
   "nn": "43",
   "benchmark": "Ginkgo GDPa1",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/gdpa1/",
   "domain": "Antibodies",
   "type": "A+B",
   "evidence_level": "L4",
   "first_release": "2025-09-08 (partly verified)",
   "latest_update": "2026-11-03 (partly verified), data",
   "status": "Low-frequency",
   "wetlab_refresh": "New",
   "models_reported": 0,
   "ranking_status": "Board",
   "current_ranking": "Board: Anonymous, 0.708 (Spearman correlation per property on the private held-out set; AbDev competition 2025, 80 private held-out antibodies, 5 properties) · Board · 2026-02-22"
  },
  {
   "nn": "08",
   "benchmark": "Basenji/Enformer test set",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/enformer/",
   "domain": "Genomics & RNA",
   "type": "B",
   "evidence_level": "L2–L3",
   "first_release": "2017-07-10 (partly verified)",
   "latest_update": "2026-01-15 (partly verified), maintenance only",
   "status": "Active",
   "wetlab_refresh": "Static",
   "models_reported": 3,
   "ranking_status": "Self-reported",
   "current_ranking": "Self-reported: The sources contain no rank-1 entry and the entries use different protocols, so no headline number is given."
  },
  {
   "nn": "11",
   "benchmark": "ClinVar hold-out protocol",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/clinvar/",
   "domain": "Genomics & RNA",
   "type": "B",
   "evidence_level": "L2–L3",
   "first_release": "2013-04 (partly verified)",
   "latest_update": "2026-11-08, data",
   "status": "Active",
   "wetlab_refresh": "Accumulating",
   "models_reported": 5,
   "ranking_status": "Not comparable",
   "current_ranking": "Not comparable: 5 results on different protocols, no single ranking"
  },
  {
   "nn": "13",
   "benchmark": "CAGI",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/cagi/",
   "domain": "Genomics & RNA",
   "type": "A",
   "evidence_level": "L4–L5",
   "first_release": "2010 (partly verified)",
   "latest_update": "2026-06-22, new round",
   "status": "Active",
   "wetlab_refresh": "New",
   "models_reported": 1,
   "ranking_status": "Third-party",
   "current_ranking": "Third-party: ClinPred / MetaRNN, AUROC 0.92 (AUROC (pathogenic vs benign missense); CAGI6 Annotate-All-Missense full evaluation set (60 predictors)) · Third-party · 2025-03-21"
  },
  {
   "nn": "16",
   "benchmark": "GUE + Nucleotide Transformer benchmark",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/nt-gue/",
   "domain": "Genomics & RNA",
   "type": "B",
   "evidence_level": "L2–L3",
   "first_release": "2022-06-10",
   "latest_update": "2025-12-25, data",
   "status": "Low-frequency",
   "wetlab_refresh": "Static",
   "models_reported": 0,
   "ranking_status": "No ranking",
   "current_ranking": "No ranking: No official board and no site model reports on these suites, so there is no headline number."
  },
  {
   "nn": "21",
   "benchmark": "DREAM5 / BEELINE / CausalBench",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/dream5/",
   "domain": "Genomics & RNA",
   "type": "A+B+C",
   "evidence_level": "L2–L5",
   "first_release": "2010 (partly verified)",
   "latest_update": "2025-03-11 (partly verified), paper revision",
   "status": "Low-frequency",
   "wetlab_refresh": "Static",
   "models_reported": 0,
   "ranking_status": "Not comparable",
   "current_ranking": "Not comparable: 3 results on different protocols, no single ranking"
  },
  {
   "nn": "37",
   "benchmark": "TraitGym",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/traitgym/",
   "domain": "Genomics & RNA",
   "type": "B",
   "evidence_level": "L3",
   "first_release": "2025-02-12",
   "latest_update": "2025-03-25 (partly verified), maintenance only",
   "status": "Low-frequency",
   "wetlab_refresh": "Static",
   "models_reported": 3,
   "ranking_status": "Board",
   "current_ranking": "Board: CADD, 0.712 (se 0.038) (AUPRC weighted-averaged by chromosome (main metric), with standard error; TraitGym Mendelian traits (matched_9) and Complex traits (matched_9), subset 'all', zero-shot and linear-probing tracks) · Board · 2025-03-07"
  },
  {
   "nn": "38",
   "benchmark": "BEND",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/bend/",
   "domain": "Genomics & RNA",
   "type": "B",
   "evidence_level": "L2",
   "first_release": "2023-11-21",
   "latest_update": "2026-11-02, new version",
   "status": "Active",
   "wetlab_refresh": "Static",
   "models_reported": 0,
   "ranking_status": "Board",
   "current_ranking": "Board: SpliceAI, 0.674 (Per-task metrics with no single official ranking metric: conditional log loss (bits/base, lower better), macro Spearman correlation, top-1 tissue identification accuracy; BEND 2.0 Table 1 snapshot: 8 endpoints across 5 capability categories, 17 model-interface rows) · Board · 2026-10-22"
  },
  {
   "nn": "39",
   "benchmark": "RNAGym",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/rnagym/",
   "domain": "Genomics & RNA",
   "type": "B",
   "evidence_level": "L2",
   "first_release": "2025-06-17",
   "latest_update": "2026-08-14 (partly verified), board entry",
   "status": "Active",
   "wetlab_refresh": "Static",
   "models_reported": 1,
   "ranking_status": "Board",
   "current_ranking": "Board: Evo 2 (40B), 0.2120 (Ribozyme 0.1081 / tRNA 0.4310 / Aptamer 0.0970) (Signed Spearman correlation, macro-averaged over three ncRNA categories with equal category weight (from v0.1.1); RNAGym fitness leaderboard, ncRNA only (31 assays); mRNA coding/splicing assays excluded) · Board · 2026-08-14 (partly verified)"
  },
  {
   "nn": "09",
   "benchmark": "scIB (+Open Problems)",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/scib/",
   "domain": "Single-cell & perturbation",
   "type": "B+C",
   "evidence_level": "L2",
   "first_release": "2020-05-23",
   "latest_update": "2026-11-01, new version",
   "status": "Active",
   "wetlab_refresh": "Accumulating",
   "models_reported": 1,
   "ranking_status": "Board",
   "current_ranking": "Board: The board orders by scaled overall mean but shows no numeric overall score; derived means are not used as a headline."
  },
  {
   "nn": "24",
   "benchmark": "Virtual Cell Challenge and perturbation benchmarks",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/vcc/",
   "domain": "Single-cell & perturbation",
   "type": "A+B+C",
   "evidence_level": "L2–L4",
   "first_release": "2024-08-20",
   "latest_update": "2026-10-22 (partly verified), new round",
   "status": "Active",
   "wetlab_refresh": "New",
   "models_reported": 9,
   "ranking_status": "Board",
   "current_ranking": "Board: Team BM_xTVC, xTrimoSCPerturb (improved scFoundation architecture with protein-model embeddings), rank 1 of 300+ final-round teams (board publishes ranks only, no numeric scores) (VCC 2025 final rank aggregating PDS, DES and MAE, with the Generalist Prize as mean rank over 7 metrics; Virtual Cell Challenge 2025 final test set (H1 hESC, held-out CRISPRi perturbations)) · Board · 2025-12-06"
  },
  {
   "nn": "10",
   "benchmark": "GuacaMol (+MOSES)",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/guacamol/",
   "domain": "Molecule generation",
   "type": "D",
   "evidence_level": "L2",
   "first_release": "2018-11-22",
   "latest_update": "2023-09-19, maintenance only",
   "status": "Frozen",
   "wetlab_refresh": "Static",
   "models_reported": 0,
   "ranking_status": "No ranking",
   "current_ranking": "No ranking: No official board and no site model reports a GuacaMol score, so no headline is given."
  },
  {
   "nn": "32",
   "benchmark": "CrossDocked2020",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/crossdocked/",
   "domain": "Molecule generation",
   "type": "D",
   "evidence_level": "L2",
   "first_release": "2020-02-20 (partly verified)",
   "latest_update": "2022-11 (partly verified), data",
   "status": "Frozen",
   "wetlab_refresh": "Static",
   "models_reported": 1,
   "ranking_status": "Not comparable",
   "current_ranking": "Not comparable: 3 results on different protocols, no single ranking"
  },
  {
   "nn": "14",
   "benchmark": "PubMedQA",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/pubmedqa/",
   "domain": "Text, LLMs & agents",
   "type": "B+E",
   "evidence_level": "L1",
   "first_release": "2019-09-13",
   "latest_update": "2023-04-18, maintenance only",
   "status": "Frozen",
   "wetlab_refresh": "Static",
   "models_reported": 2,
   "ranking_status": "Board",
   "current_ranking": "Board: GPT-4 (Medprompt), 82.0 (Accuracy (%) (macro-F1 mostly not reported), reasoning-required setting; PQA-L test (500 questions)) · Board · 2024-04-18"
  },
  {
   "nn": "18",
   "benchmark": "LAB-Bench / LABBench2",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/labbench/",
   "domain": "Text, LLMs & agents",
   "type": "E",
   "evidence_level": "L1–L2",
   "first_release": "2024-07-14",
   "latest_update": "2026-10-23, maintenance only",
   "status": "Active",
   "wetlab_refresh": "Static",
   "models_reported": 3,
   "ranking_status": "Board",
   "current_ranking": "Board: gpt-5-2, 0.609 (Tools + high); Base 0.345 (LABBench2 aggregate score (mean across sub-benchmarks), settings 'Tools + high' and 'Base'; LABBench2 (1,912 tasks, 11 categories)) · Board · 2026-03-23"
  },
  {
   "nn": "23",
   "benchmark": "BioASQ",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/bioasq/",
   "domain": "Text, LLMs & agents",
   "type": "A+B",
   "evidence_level": "L1–L4",
   "first_release": "2013 (partly verified)",
   "latest_update": "2026-09, results",
   "status": "Active",
   "wetlab_refresh": "Accumulating",
   "models_reported": 0,
   "ranking_status": "Board",
   "current_ranking": "Board: mckpt2, Yes/No F1 0.9481, Acc. 0.9524; Factoid MRR 0.2000; List F1 0.1537 (Yes/no macro-F1 as the ranking key of Tables 7 and 8, plus factoid MRR and list F1; BioASQ Task 14b batch 2 exact answers, phase A+ (Table 7) and phase B (Table 8); preliminary results) · Board · 2026-09 (partly verified)"
  },
  {
   "nn": "29",
   "benchmark": "BixBench",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/bixbench/",
   "domain": "Text, LLMs & agents",
   "type": "E",
   "evidence_level": "L2",
   "first_release": "2025-02-28 (partly verified)",
   "latest_update": "2026-10-16 (partly verified), board entry",
   "status": "Active",
   "wetlab_refresh": "Static",
   "models_reported": 3,
   "ranking_status": "Board",
   "current_ranking": "Board: gemini-4-argon, 0.523 (Average score over the successor's 20 tasks, scored programmatically against source papers; BixBench3 (successor benchmark, 20 research-study-scale tasks)) · Board · 2026-11-16"
  },
  {
   "nn": "41",
   "benchmark": "BioML-bench",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/bioml-bench/",
   "domain": "Text, LLMs & agents",
   "type": "E",
   "evidence_level": "L2",
   "first_release": "2025-09-04",
   "latest_update": "2025-09-28, paper revision",
   "status": "Low-frequency",
   "wetlab_refresh": "Static",
   "models_reported": 1,
   "ranking_status": "Self-reported",
   "current_ranking": "Self-reported: The source has no rank-1 entry: entries are unranked or protocol-specific, so the caveat is shown as for a not-comparable cell."
  },
  {
   "nn": "42",
   "benchmark": "BioMysteryBench",
   "url": "https://sparkscience.xyz/bio/benchmark/benchmarks/biomysterybench/",
   "domain": "Text, LLMs & agents",
   "type": "E",
   "evidence_level": "L2–L4",
   "first_release": "2026-04-29",
   "latest_update": "2026-11-09 (partly verified), board entry",
   "status": "Active",
   "wetlab_refresh": "Static",
   "models_reported": 1,
   "ranking_status": "Third-party",
   "current_ranking": "Third-party: Claude Fable 5.2, 83.70% (Final-answer accuracy, mean of three full runs, scored by a judge model; Third-party board run: Terminus 2 harness, 200 turns / 4 h per task) · Third-party · 2026-11-09 (partly verified)"
  }
 ]
}