{
 "as_of": "2026-11-16",
 "relation_types": {
  "official-participation": "organizer results or leaderboard under an identifiable name (counted, established)",
  "self-reported-official-protocol": "developer reports on the official split/protocol, not on a board (counted, established)",
  "self-reported-modified-protocol": "developer reports with different filtering/subset/sampling, or self-reported participation the organizer has not confirmed (counted, established)",
  "third-party-evaluation": "only third parties ran the model on the benchmark (ADDED this round by owner decision; counted, established)",
  "retrospective-dataset-use": "post-hoc reuse of a released round's data (established under this round's definition, but shown separately and never as participation)",
  "cited-as-comparison-only": "the model appears only as a baseline number copied from elsewhere, or only the tool is used (NOT established)",
  "disputed-or-unconfirmed": "claimed or second-hand, not verifiable (NOT established)",
  "not-a-pairing": "recorded decision that no pairing exists"
 },
 "established_definition": "relation type other than disputed-or-unconfirmed and cited-as-comparison-only (not-a-pairing records are decisions, not pairings).",
 "pairings": [
  {
   "model": "model-massivefold",
   "benchmark": "bench-01-casp",
   "nn": "01",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "CASP16, five models per target selected by confidence",
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "medium",
   "verification": "unverified",
   "note": "Group took part in CASP16",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-opencomplex2",
   "benchmark": "bench-01-casp",
   "nn": "01",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": null,
   "evidence_url": "https://predictioncenter.org/casp16/index.cgi",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "CASP16 participant with a talk at the CASP16 meeting; official ranks not found",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-rna-structure-models",
   "benchmark": "bench-01-casp",
   "nn": "01",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "CASP16 automated-server section (trRosettaRNA2); CASP15 retrospective (RhoFold+)",
   "evidence_url": "https://www.nature.com/articles/s41592-024-02487-0",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Family entry: trRosettaRNA2 (server) took part in CASP16; RhoFold+ is a CASP15 retrospective evaluation",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-alphafold3",
   "benchmark": "bench-01-casp",
   "nn": "01",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": "CASP15 public RNA targets",
   "evidence_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11168924/",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "AF3 paper used CASP15 RNA targets post hoc; in CASP16 AF3 is only a component of other groups, no own entry",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-aqaffinity",
   "benchmark": "bench-01-casp",
   "nn": "01",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": null,
   "evidence_url": "https://www.sandboxaq.com/post/aqaffinity-open-source-structure-to-affinity-built-on-openfold3-by-sandboxaq",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "CASP16 L1000/L3000 post hoc, figure only, L3000 overlaps training",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-boltz-2",
   "benchmark": "bench-01-casp",
   "nn": "01",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": "affinity track, retrospective (2 targets / 140 pairs)",
   "evidence_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12262699/",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Retrospective CASP16 affinity data (2 targets, 140 pairs); not a blind participation",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-chai-1",
   "benchmark": "bench-01-casp",
   "nn": "01",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": "protein monomers of one past season",
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "medium",
   "verification": "unverified",
   "note": "CASP15 monomer LDDT, second-hand quote only; post hoc",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-esm3",
   "benchmark": "bench-01-casp",
   "nn": "01",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": "CASP14 (71 targets) and CASP15 (70 targets) time-held-out structure and contact prediction",
   "evidence_url": "https://www.biorxiv.org/content/10.1101/2024.07.01.600583v2.full",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "CASP14/15 time-split post hoc",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-isodde",
   "benchmark": "bench-01-casp",
   "nn": "01",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": null,
   "evidence_url": "https://zenodo.org/records/18606681",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "CASP16 blind affinity data used post hoc, figure only",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-nesso-1",
   "benchmark": "bench-01-casp",
   "nn": "01",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": null,
   "evidence_url": "https://www.valencelabs.com/wp-content/uploads/2026/07/nesso1.pdf",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Added as a missing candidate in round 7 and confirmed in review.",
   "resolution": "Post-hoc use of the released affinity set (140 complexes, 2 targets), not participation in the blind round; the same rule applies to DPLM-2 × CAMEO.",
   "origin": "added (R7 missing candidate / review)"
  },
  {
   "model": "model-neuralplexer3",
   "benchmark": "bench-01-casp",
   "nn": "01",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/html/2412.10743v2",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Matrix marks a self-report, but page evidence is only CASP15 RNA, duplicated from the RNA-Puzzles column",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-openfold3",
   "benchmark": "bench-01-casp",
   "nn": "01",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": "CASP16 protein and RNA monomers (post hoc)",
   "evidence_url": "https://github.com/aqlaboratory/openfold-3",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "CASP16 protein/RNA monomers, README figure only, post hoc",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-profluent-e1",
   "benchmark": "bench-01-casp",
   "nn": "01",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": null,
   "evidence_url": "https://www.biorxiv.org/content/10.1101/2025.11.12.688125v1.full",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "CASP15 contact maps, numbers not retrieved",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-terrabind",
   "benchmark": "bench-01-casp",
   "nn": "01",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/abs/2602.07735",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Retrospective CASP16 affinity evaluation",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-xtrimopglm",
   "benchmark": "bench-01-casp",
   "nn": "01",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/abs/2401.06199",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Post hoc on CASP15 (n=56)",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-enchant-v1-v2",
   "benchmark": "bench-01-casp",
   "nn": "01",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://www.iambic.ai/news/enchant-3",
   "evidence_site_page_only": false,
   "confidence": "low",
   "verification": "disputed",
   "note": "v3 page claims held-out structures from this round, figure only, no protocol; split from a combined candidate and kept unconfirmed.",
   "resolution": null,
   "origin": "added (R7 missing candidate)"
  },
  {
   "model": "model-esm-c",
   "benchmark": "bench-02-proteingym",
   "nn": "02",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "DMS substitutions zero-shot, maintainer-run summary table (updated 2025-06-13); 300M and 600M entries",
   "evidence_url": "https://proteingym.org/",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Entry on the official summary table",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-esm3",
   "benchmark": "bench-02-proteingym",
   "nn": "02",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "DMS substitutions zero-shot, maintainer-run summary table (updated 2025-06-13); open 1.4B entry",
   "evidence_url": "https://proteingym.org/",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Entry on the official summary table",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-progen3",
   "benchmark": "bench-02-proteingym",
   "nn": "02",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": null,
   "evidence_url": "https://proteingym.org/",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Entry on the official summary table",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-prosst",
   "benchmark": "bench-02-proteingym",
   "nn": "02",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "zero-shot substitution DMS summary table, several structure-vocabulary sizes",
   "evidence_url": "https://proteingym.org/",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Entry on the official summary table",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-saprot",
   "benchmark": "bench-02-proteingym",
   "nn": "02",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "zero-shot substitution DMS summary",
   "evidence_url": "https://proteingym.org/",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Entry on the official summary table",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-venusrem",
   "benchmark": "bench-02-proteingym",
   "nn": "02",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "zero-shot substitution official summary table (Structure & MSA category)",
   "evidence_url": "https://proteingym.org/",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Entry on the official summary table",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-xtrimopglm",
   "benchmark": "bench-02-proteingym",
   "nn": "02",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": null,
   "evidence_url": "https://proteingym.org/",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Entry on the official summary table",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-poet-2",
   "benchmark": "bench-02-proteingym",
   "nn": "02",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": "zero-shot (substitutions, indels, higher-order, clinical) plus supervised settings",
   "evidence_url": "https://arxiv.org/html/2508.04724v1",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Paper table claims the official protocol; not found on the official table",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-profluent-e1",
   "benchmark": "bench-02-proteingym",
   "nn": "02",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://github.com/Profluent-AI/E1#comparison-to-other-models",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Only a curve in the project README; no row on the official summary table",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-frontier-llms",
   "benchmark": "bench-02-proteingym",
   "nn": "02",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": null,
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "low",
   "verification": "unverified",
   "note": "Scores from a second-hand aggregator; the entry is a family, not one model",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-molformer-xl",
   "benchmark": "bench-03-moleculenet",
   "nn": "03",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/abs/2106.09553",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "MoleculeNet scaffold/random splits",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-uni-mol2",
   "benchmark": "bench-03-moleculenet",
   "nn": "03",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/html/2406.14969v2",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "QM9 only, scaffold split",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-chemprop-v2",
   "benchmark": "bench-03-moleculenet",
   "nn": "03",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/abs/1904.01561",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "disputed",
   "note": "Page marks it unconfirmed; numbers belong to the 2019 original",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-admet-ai",
   "benchmark": "bench-04-tdc",
   "nn": "04",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": null,
   "evidence_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11226862/",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Submitted to the TDC ADMET group board (only one Caco2 row on the live board)",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-minimol",
   "benchmark": "bench-04-tdc",
   "nn": "04",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/abs/2404.14986",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Self paper plus official board entries",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-mole",
   "benchmark": "bench-04-tdc",
   "nn": "04",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": null,
   "evidence_url": "https://doi.org/10.1038/s41467-024-53751-y",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Paper compares with a 2023-09 board snapshot; no row on the live boards",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-txgemma",
   "benchmark": "bench-04-tdc",
   "nn": "04",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/abs/2504.06196",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "66 TDC tasks, recommended splits",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-chemprop-v2",
   "benchmark": "bench-04-tdc",
   "nn": "04",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://tdcommons.ai/benchmark/admet_group/01caco2/",
   "evidence_site_page_only": false,
   "confidence": "low",
   "verification": "disputed",
   "note": "Unversioned board entries, linked indirectly via ADMET-AI",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-enchant-v1-v2",
   "benchmark": "bench-04-tdc",
   "nn": "04",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://www.iambic.ai/post/enchant",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "disputed",
   "note": "Obach human PK result not shown to use the TDC split; three site surfaces unified to unconfirmed",
   "resolution": "The developer post never names the benchmark, the official split or the protocol; the comparison is a hyperlink to a baseline page. The published surfaces disagree three ways (zh matrix 'self', zh model page 'unconfirmed', en pairs.json 'self'); all three are unified to unconfirmed. Not an established pairing.",
   "origin": "original-183 (resolved)"
  },
  {
   "model": "model-alphafold3",
   "benchmark": "bench-05-posebusters",
   "nn": "05",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": "PoseBusters V1 (428), official set",
   "evidence_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11168924/",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Self-report on the official V1 set; V2 numbers are third-party recomputations",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-chai-1",
   "benchmark": "bench-05-posebusters",
   "nn": "05",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": "PoseBusters V1 (428), official set",
   "evidence_url": "https://doi.org/10.1101/2024.10.10.615955",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "V1 self-report (preprint, quoted via reviews); the V2 numbers are third-party",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-neuralplexer3",
   "benchmark": "bench-05-posebusters",
   "nn": "05",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/abs/2412.10743",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "V2 set, with validity checks included",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-protenix",
   "benchmark": "bench-05-posebusters",
   "nn": "05",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": "official set, early version only (via the Mini paper)",
   "evidence_url": "https://arxiv.org/html/2507.11839v1",
   "evidence_site_page_only": false,
   "confidence": "low",
   "verification": "unverified",
   "note": "Only an early version's table; current versions report no score on this set, so the matrix cell overstated it",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-intellifold-2",
   "benchmark": "bench-05-posebusters",
   "nn": "05",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": "PoseBusters V2 (README, steering option)",
   "evidence_url": "https://github.com/IntelliGen-AI/IntelliFold",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Approximate values in the repository README with a steering option; no table",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-nesso-1",
   "benchmark": "bench-05-posebusters",
   "nn": "05",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://www.valencelabs.com/wp-content/uploads/2026/07/nesso1.pdf",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "A missing candidate added and confirmed in the review",
   "resolution": "The same sentence names this benchmark; its poses are coarse-grained, so the physical-validity checks are not run as on all-atom predictions, hence modified protocol.",
   "origin": "added (R7 missing candidate / review)"
  },
  {
   "model": "model-pearl",
   "benchmark": "bench-05-posebusters",
   "nn": "05",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": "PoseBusters V2, best@5 with PB-valid filter",
   "evidence_url": "https://arxiv.org/html/2510.24670v2",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Mixes its own best@5 with another model's top-confidence result; one model excluded for its cutoff",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-terrabind",
   "benchmark": "bench-05-posebusters",
   "nn": "05",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/abs/2602.07735",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Merged into a chart with two other benchmarks; no number for this benchmark alone",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-boltz-1-1x",
   "benchmark": "bench-05-posebusters",
   "nn": "05",
   "relation": "cited-as-comparison-only",
   "source_type": "third",
   "eval_set": "PoseBusters V2, best@5",
   "evidence_url": "https://arxiv.org/abs/2510.24670",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Numbers come from another paper, not a self-report",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-diffdock",
   "benchmark": "bench-05-posebusters",
   "nn": "05",
   "relation": "cited-as-comparison-only",
   "source_type": "third",
   "eval_set": "PoseBusters V2 comparison table in a third-party paper",
   "evidence_url": "https://arxiv.org/abs/2412.10743",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Quoted from the comparison table of another model's paper",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-vina",
   "benchmark": "bench-05-posebusters",
   "nn": "05",
   "relation": "cited-as-comparison-only",
   "source_type": "third",
   "eval_set": "PoseBusters V2 with known pocket, from a third-party comparison table",
   "evidence_url": "https://arxiv.org/abs/2412.10743",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Quoted from the comparison table of another model's paper",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-chemformer",
   "benchmark": "bench-07-uspto",
   "nn": "07",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://doi.org/10.1088/2632-2153/ac3ffb",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "USPTO-50K; the Uni-Mol3 re-quote is comparison only",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-retrodfm-r",
   "benchmark": "bench-07-uspto",
   "nn": "07",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/html/2507.17448v1",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "USPTO-50K/FULL; with test-time augmentation noted",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-scireasoner",
   "benchmark": "bench-07-uspto",
   "nn": "07",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "high",
   "verification": "unverified",
   "note": "USPTO-50K single-step retrosynthesis, matrix note only, unverified",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-uni-mol3",
   "benchmark": "bench-07-uspto",
   "nn": "07",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/html/2508.00920v2",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "USPTO-MIT/50K/Condition",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-ether0",
   "benchmark": "bench-07-uspto",
   "nn": "07",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/abs/2506.17238",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Self-built reaction prediction, not official test set",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-alphagenome",
   "benchmark": "bench-08-enformer",
   "nn": "08",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://doi.org/10.1038/s41586-025-10014-0",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Self-reported on this data's track test set",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-borzoi",
   "benchmark": "bench-08-enformer",
   "nn": "08",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://doi.org/10.1038/s41588-024-02053-6",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "The paper uses its own variant tasks and also reports on this test set",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-ntv3",
   "benchmark": "bench-08-enformer",
   "nn": "08",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://instadeep.com/wp-content/uploads/2025/12/NT_v3.pdf",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Self-report in a technical report, fine-tuned on re-folded splits",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-scgpt-geneformer",
   "benchmark": "bench-09-scib",
   "nn": "09",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": "PBMC 10K",
   "evidence_url": "https://www.biorxiv.org/content/10.1101/2023.04.30.538439v2.full",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "scGPT only (PBMC10K), self-reported; Geneformer not applicable; family entry",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-aido-cell",
   "benchmark": "bench-09-scib",
   "nn": "09",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://huggingface.co/genbio-ai/GB.Cell-100M",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "disputed",
   "note": "Model card claims zero-shot clustering SOTA; scIB not named, no numbers",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-scprint-2",
   "benchmark": "bench-09-scib",
   "nn": "09",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://www.biorxiv.org/content/10.64898/2025.12.11.693702v1",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "disputed",
   "note": "Abstract does not name scIB",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-alphagenome",
   "benchmark": "bench-11-clinvar",
   "nn": "11",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://doi.org/10.1038/s41586-025-10014-0",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Its own variant-effect suite, including splicing classes from this database",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-alphamissense",
   "benchmark": "bench-11-clinvar",
   "nn": "11",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://doi.org/10.1126/science.adg7492",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Its own missense test set",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-bioreason",
   "benchmark": "bench-11-clinvar",
   "nn": "11",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/abs/2505.23579v2",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Its own pathway question task, not this protocol",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-evo-2",
   "benchmark": "bench-11-clinvar",
   "nn": "11",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13128491/",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Its own subsets, figure-only",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-popeve",
   "benchmark": "bench-11-clinvar",
   "nn": "11",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12695638/",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "An expert-curated subset from earlier years",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-diffdock",
   "benchmark": "bench-12-dude",
   "nn": "12",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": "LIT-PCBA virtual-screening study by a third party",
   "evidence_url": "https://arxiv.org/abs/2605.01681",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Third-party LIT-PCBA study (arXiv 2605.01681)",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-vina",
   "benchmark": "bench-12-dude",
   "nn": "12",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": "LIT-PCBA, rerun by a third-party study",
   "evidence_url": "https://arxiv.org/pdf/2605.01681",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Third-party LIT-PCBA study ran AutoDock/GNINA",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-alphafold3",
   "benchmark": "bench-12-dude",
   "nn": "12",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "low",
   "verification": "disputed",
   "note": "Only a second-hand pose claim in an RSC 2026 paper; no numbers; the benchmark paper does not evaluate AF3",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-boltz-2",
   "benchmark": "bench-12-dude",
   "nn": "12",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": "decoy-set screening in a third-party paper",
   "evidence_url": "https://pubs.rsc.org/en/content/articlelanding/2026/sc/d5sc06481c",
   "evidence_site_page_only": false,
   "confidence": "low",
   "verification": "disputed",
   "note": "Third-party paper uses DEKOIS 2.0 etc., not clearly DUD-E/LIT-PCBA; second-hand",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-protenix",
   "benchmark": "bench-12-dude",
   "nn": "12",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "low",
   "verification": "disputed",
   "note": "Second-hand LIT-PCBA mention, no numbers",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-alphamissense",
   "benchmark": "bench-13-cagi",
   "nn": "13",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": null,
   "evidence_url": "https://link.springer.com/article/10.1007/s00439-025-02732-2",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Post-hoc third-party evaluation on CAGI6 (checked at abstract level)",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-frontier-llms",
   "benchmark": "bench-14-pubmedqa",
   "nn": "14",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/html/2604.05081",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Gemini 3 figures self-reported in the MedGemma 1.5 report; earlier board entries (GPT-4, Claude 3) were self-submitted.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-medgemma-med-gemini",
   "benchmark": "bench-14-pubmedqa",
   "nn": "14",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/html/2507.05201",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "MedGemma 4B, 27B and 1.5 reported; Med-Gemini does not report PubMedQA.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-co-scientist",
   "benchmark": "bench-14-pubmedqa",
   "nn": "14",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/abs/2502.18864",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report found in official materials",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-gpt-rosalind",
   "benchmark": "bench-14-pubmedqa",
   "nn": "14",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report found",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-intern-s",
   "benchmark": "bench-14-pubmedqa",
   "nn": "14",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://github.com/InternLM/Intern-S1",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report found in official materials",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-quine",
   "benchmark": "bench-14-pubmedqa",
   "nn": "14",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://www.microsoft.com/en-us/research/blog/introducing-quine-an-ai-research-system-designed-for-the-complexity-of-biology/",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report found in official materials",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-scireasoner",
   "benchmark": "bench-14-pubmedqa",
   "nn": "14",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "high",
   "verification": "disputed",
   "note": "Not in the paper text",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-verid",
   "benchmark": "bench-14-pubmedqa",
   "nn": "14",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report found in official materials",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-alphafold3",
   "benchmark": "bench-15-cameo",
   "nn": "15",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "operator-run complex and ligand baseline, 2024-01 to 2025-06",
   "evidence_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12750032/",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "CAMEO operators ran AF3 as a baseline (2025 assessment paper); maintainer-run, not a developer submission.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-dplm-2",
   "benchmark": "bench-15-cameo",
   "nn": "15",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": "frozen 2022 target set, folding and inverse folding",
   "evidence_url": "https://arxiv.org/html/2410.13782v1",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Uses a frozen 2022 target set; no live submission, no service ranking.",
   "resolution": "The paper uses a frozen 2022 target set derived from the service, with no live submission and no service-assigned ranking. Recorded as a relation rather than deleted, so the rule matches Nesso-1 x CASP16.",
   "origin": "added (R7 missing candidate)"
  },
  {
   "model": "model-profluent-e1",
   "benchmark": "bench-15-cameo",
   "nn": "15",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": null,
   "evidence_url": "https://github.com/Profluent-AI/E1#comparison-to-other-models",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "CAMEO targets used post hoc; curve only.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-xtrimopglm",
   "benchmark": "bench-15-cameo",
   "nn": "15",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/abs/2401.06199",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "CAMEO 2022-04 to 06 static set, n=194.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-enchant-v1-v2",
   "benchmark": "bench-15-cameo",
   "nn": "15",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://www.iambic.ai/news/enchant-3",
   "evidence_site_page_only": false,
   "confidence": "low",
   "verification": "disputed",
   "note": "Same source; static 2022 set, figure only. Unconfirmed; would count as retrospective use, not participation.",
   "resolution": null,
   "origin": "added (R7 missing candidate)"
  },
  {
   "model": "model-scireasoner",
   "benchmark": "bench-17-cafa",
   "nn": "17",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/html/2607.07708",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "disputed",
   "note": "Self-reports on DeepFRI-GO; CAFA-3 only in a figure caption, a modified protocol if kept; paper identity unresolved (two same-name papers).",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-frontier-llms",
   "benchmark": "bench-18-labbench",
   "nn": "18",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "LABBench2",
   "evidence_url": "https://futurehouse.org/articles/lab-bench-measuring-capabilities-of-language-models-for-biology-research",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "LABBench2 official board entries; family entry.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-biomni",
   "benchmark": "bench-18-labbench",
   "nn": "18",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": "LAB-Bench DbQA/SeqQA subsets",
   "evidence_url": "https://doi.org/10.1101/2025.05.30.656746",
   "evidence_site_page_only": false,
   "confidence": "low",
   "verification": "unverified",
   "note": "Original DbQA/SeqQA subsets with 45 dev / 315 hidden test questions and 3 runs.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-gpt-rosalind",
   "benchmark": "bench-18-labbench",
   "nn": "18",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://openai.com/index/introducing-gpt-rosalind/",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "11 of 15 LABBench2 tasks, qualitative only.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-co-scientist",
   "benchmark": "bench-18-labbench",
   "nn": "18",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/abs/2502.18864",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report found in official materials",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-intern-s",
   "benchmark": "bench-18-labbench",
   "nn": "18",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://github.com/InternLM/Intern-S1",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report found in official materials",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-quine",
   "benchmark": "bench-18-labbench",
   "nn": "18",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://www.microsoft.com/en-us/research/blog/introducing-quine-an-ai-research-system-designed-for-the-complexity-of-biology/",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report found in official materials",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-scireasoner",
   "benchmark": "bench-18-labbench",
   "nn": "18",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "high",
   "verification": "disputed",
   "note": "Not in the paper text",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-verid",
   "benchmark": "bench-18-labbench",
   "nn": "18",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report found in official materials",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-genmol",
   "benchmark": "bench-19-pmo",
   "nn": "19",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://github.com/NVIDIA-Digital-Bio/genmol",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "PMO 23 tasks, original protocol",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-reasyn-v2",
   "benchmark": "bench-19-pmo",
   "nn": "19",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/html/2509.16084v2",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Uses 15 TDC oracle tasks rather than the full 23",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-reinvent-4",
   "benchmark": "bench-19-pmo",
   "nn": "19",
   "relation": "cited-as-comparison-only",
   "source_type": "third",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/abs/2206.12411",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "The PMO paper used the prior-generation REINVENT as a baseline; REINVENT 4 itself reports no PMO score.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-scgpt-geneformer",
   "benchmark": "bench-21-dream5",
   "nn": "21",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/abs/2602.17532",
   "evidence_site_page_only": false,
   "confidence": "low",
   "verification": "disputed",
   "note": "A third-party attention-edge study, read in abstract only.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-scprint-2",
   "benchmark": "bench-21-dream5",
   "nn": "21",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://www.biorxiv.org/content/10.64898/2025.12.11.693702v1",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "disputed",
   "note": "The preprint mentions its own GRN benchmark with scores in the body, not under this family's protocol.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-af2-multimer",
   "benchmark": "bench-22-capri",
   "nn": "22",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "CASP15-CAPRI official assessment, assessor-run yardstick baseline",
   "evidence_url": "https://pubmed.ncbi.nlm.nih.gov/37905971/",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "The official round assessment lists it as the assessors' yardstick baseline, counted as an official entry; no per-target numbers.",
   "resolution": null,
   "origin": "added (R7 missing candidate)"
  },
  {
   "model": "model-massivefold",
   "benchmark": "bench-22-capri",
   "nn": "22",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "CASP16-CAPRI Round 57 (Round 58 data also released)",
   "evidence_url": "https://doi.org/10.1101/2025.05.26.653955",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Took part in Round 57 (CASP16-CAPRI); self-reports 31 targets and 65 interfaces, with no rank.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-alphafold3",
   "benchmark": "bench-22-capri",
   "nn": "22",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": "CASP16 complexes",
   "evidence_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12750027/",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "disputed",
   "note": "No standalone entry appears in the official CAPRI assessment material; only secondary sources call it a component of most pipelines.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-co-scientist",
   "benchmark": "bench-23-bioasq",
   "nn": "23",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/abs/2502.18864",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report by it was found in the official material.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-frontier-llms",
   "benchmark": "bench-23-bioasq",
   "nn": "23",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://ceur-ws.org/Vol-4283/paper1.pdf",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "disputed",
   "note": "The overview ranks submitted systems, not the underlying LLMs.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-gpt-rosalind",
   "benchmark": "bench-23-bioasq",
   "nn": "23",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report was found.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-intern-s",
   "benchmark": "bench-23-bioasq",
   "nn": "23",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://github.com/InternLM/Intern-S1",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report by it was found in the official material.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-medgemma-med-gemini",
   "benchmark": "bench-23-bioasq",
   "nn": "23",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://ceur-ws.org/Vol-4283/paper1.pdf",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "disputed",
   "note": "The overview scores whole systems and contains no standalone figure for it, so the board marking in the matrix is unsupported.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-quine",
   "benchmark": "bench-23-bioasq",
   "nn": "23",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://www.microsoft.com/en-us/research/blog/introducing-quine-an-ai-research-system-designed-for-the-complexity-of-biology/",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report by it was found in the official material.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-scireasoner",
   "benchmark": "bench-23-bioasq",
   "nn": "23",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "high",
   "verification": "disputed",
   "note": "Not found in the paper text.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-verid",
   "benchmark": "bench-23-bioasq",
   "nn": "23",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report by it was found in the official material.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-xtrimoscperturb-scfoundation",
   "benchmark": "bench-24-vcc",
   "nn": "24",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": null,
   "evidence_url": "https://arcinstitute.org/news/virtual-cell-challenge-2025-wrap-up",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Overall winner of VCC 2025 per the organizer wrap-up; scores unpublished.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-c2s-scale",
   "benchmark": "bench-24-vcc",
   "nn": "24",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://www.biorxiv.org/content/10.1101/2025.04.14.648850v1.full",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Uses its own datasets and metrics, not the VCC protocol.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-cellfm",
   "benchmark": "bench-24-vcc",
   "nn": "24",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://www.nature.com/articles/s41467-025-59926-5",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Adamson and Norman data through GEARS, not VCC.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-stack",
   "benchmark": "bench-24-vcc",
   "nn": "24",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://doi.org/10.64898/2026.01.09.698608",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Own perturbation sets; its VCC claim is rejected on the model page.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-state",
   "benchmark": "bench-24-vcc",
   "nn": "24",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://arcinstitute.org/news/virtual-cell-model-state",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Self-reported with cell-eval on Tahoe-100M; its VCC blind score is unpublished.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-tahoe-x1",
   "benchmark": "bench-24-vcc",
   "nn": "24",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://doi.org/10.1101/2025.10.23.683759",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "An own benchmark, explicitly not VCC.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-x-cell",
   "benchmark": "bench-24-vcc",
   "nn": "24",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://xaira-therapeutics.github.io/X-Cell",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Own held-out iPSC set; VCC participation unconfirmed.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-lingshu-cell",
   "benchmark": "bench-24-vcc",
   "nn": "24",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/pdf/2603.25240",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "A post-hoc evaluation on the VCC H1 leaderboard rather than participation.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-scgpt-geneformer",
   "benchmark": "bench-24-vcc",
   "nn": "24",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": null,
   "evidence_url": "https://doi.org/10.1038/s41592-025-02772-6",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Independent third-party evaluations on Norman and Adamson data.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-neuralplexer3",
   "benchmark": "bench-25-rnapuzzles",
   "nn": "25",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/html/2412.10743v2",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "CASP15 RNA 8-target subset; AF3 baseline copied from its paper, not rerun",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-rnapro",
   "benchmark": "bench-25-rnapuzzles",
   "nn": "25",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": "RNA-Puzzles subset within a competition private leaderboard",
   "evidence_url": "https://www.biorxiv.org/content/10.64898/2025.12.30.696949.full.pdf",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "10-target RNA-Puzzles subset inside Kaggle private leaderboard",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-rna-structure-models",
   "benchmark": "bench-25-rnapuzzles",
   "nn": "25",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": "single-chain RNA-Puzzles targets, retrospective (RhoFold+)",
   "evidence_url": "https://www.nature.com/articles/s41592-024-02487-0",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "RhoFold+ retrospective on 24 RNA-Puzzles; DRfold2/trRosettaRNA2 unconfirmed; family cell",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-alphafold3",
   "benchmark": "bench-25-rnapuzzles",
   "nn": "25",
   "relation": "cited-as-comparison-only",
   "source_type": "third",
   "eval_set": "CASP15 RNA, quoted in another paper",
   "evidence_url": "https://arxiv.org/abs/2412.10743",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "CASP15 RNA value from its own paper, quoted by NeuralPLexer3; not RNA-Puzzles proper",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-saprot",
   "benchmark": "bench-26-flip",
   "nn": "26",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": "Meltome human-cell (called Thermostability in the paper); AAV 2-vs-rest",
   "evidence_url": "https://proceedings.iclr.cc/paper_files/paper/2024/file/1c42513b8895ab11fbbb5b7e8e6b6b02-Paper-Conference.pdf",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Self-reported on two datasets; a third-party re-evaluation also exists",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-xtrimopglm",
   "benchmark": "bench-26-flip",
   "nn": "26",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/abs/2401.06199",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Self-reported after fine-tuning on the random control split",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-chemprop-v2",
   "benchmark": "bench-27-polaris",
   "nn": "27",
   "relation": "cited-as-comparison-only",
   "source_type": "third",
   "eval_set": null,
   "evidence_url": "https://chemrxiv.org/engage/chemrxiv/article-details/6841f19f",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Anonymous baseline in the organiser report; comparison only",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-beacon",
   "benchmark": "bench-27-polaris",
   "nn": "27",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://openadmet.ghost.io/lessons-learned-from-the-openadmet-expansionrx-blind-challenge/",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "disputed",
   "note": "Press release only; organiser anonymises entries; model identity unverified",
   "resolution": "Two reasons. (1) Identity: organiser boards are pseudonymous, so the public model version cannot be matched to entries; first-place claims rest on a company press release, only one corroborated by a third-party write-up. (2) Scope: this entry covers Polaris-hosted challenges only, and ExpansionRx and PXR were run by OpenADMET off the hub. Not established.",
   "origin": "original-183 (resolved)"
  },
  {
   "model": "model-boltz-2",
   "benchmark": "bench-27-polaris",
   "nn": "27",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "low",
   "verification": "disputed",
   "note": "Site page says it matched the antiviral top 5 without fine-tuning; no numbers; participation not openly verified",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-bindcraft",
   "benchmark": "bench-28-adaptyv",
   "nn": "28",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "Nipah and EGFR rounds",
   "evidence_url": "https://adaptyvbio.substack.com/p/protein-design-competition-results",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "The developers took part; an early-round top-10 placement comes from an organiser post (second-hand)",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-mosaic",
   "benchmark": "bench-28-adaptyv",
   "nn": "28",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": null,
   "evidence_url": "https://proteinbase.com/collections/nipah-binder-competition-results",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Entrant in the 2025 de novo track with results on the organiser site; hit rates are self-reported",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-proteina-complexa",
   "benchmark": "bench-28-adaptyv",
   "nn": "28",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://research.nvidia.com/labs/genair/proteina-complexa/",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Added by R7/fc_zero as a missing candidate and confirmed in the review.",
   "resolution": "The project page states participation and links the organiser's competition page, but the organiser page does not name the model, so this is self-reported participation that the organiser has not confirmed - which the schema routes to self-reported-modified-protocol, not official-participation. Established, so this model also leaves the zero-pairing list.",
   "origin": "added (R7 missing candidate / review)"
  },
  {
   "model": "model-claude-protein-design",
   "benchmark": "bench-28-adaptyv",
   "nn": "28",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": null,
   "evidence_url": "https://adaptyvbio.substack.com/p/case-study-benchmarking-claudes-protein",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Organizer-run anonymous external test on 16 prior-competition targets; not a public competition",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-frontier-llms",
   "benchmark": "bench-29-bixbench",
   "nn": "29",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "BixBench3",
   "evidence_url": "https://arxiv.org/html/2503.00096v3",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Successor's official board; counted as one family cell",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-kosmos",
   "benchmark": "bench-29-bixbench",
   "nn": "29",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": "original BixBench",
   "evidence_url": "https://edisonscientific.com/news/introducing-edison-analysis",
   "evidence_site_page_only": false,
   "confidence": "low",
   "verification": "unverified",
   "note": "Self-report on the original; the product's mapping to this site entry is unclear and it is not on the successor's board",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-biomni",
   "benchmark": "bench-29-bixbench",
   "nn": "29",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": "BixBench full + verified-50",
   "evidence_url": "https://phylo.bio/blog/evaluating-ai-agents-in-biology",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Run by its developer on the full set and a verified subset with its own agent harness",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-co-scientist",
   "benchmark": "bench-29-bixbench",
   "nn": "29",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/abs/2502.18864",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report found in official materials",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-gpt-rosalind",
   "benchmark": "bench-29-bixbench",
   "nn": "29",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://the-decoder.com/openai-launches-gpt-rosalind-a-reasoning-model-built-for-life-sciences-research/",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "disputed",
   "note": "Version unspecified and the numbers appear only in second-hand reports",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-intern-s",
   "benchmark": "bench-29-bixbench",
   "nn": "29",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://github.com/InternLM/Intern-S1",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report found in official materials",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-quine",
   "benchmark": "bench-29-bixbench",
   "nn": "29",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://www.microsoft.com/en-us/research/blog/introducing-quine-an-ai-research-system-designed-for-the-complexity-of-biology/",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report found in official materials",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-scireasoner",
   "benchmark": "bench-29-bixbench",
   "nn": "29",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "high",
   "verification": "disputed",
   "note": "Not found in the paper text",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-verid",
   "benchmark": "bench-29-bixbench",
   "nn": "29",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report found in official materials",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-isodde",
   "benchmark": "bench-30-plinder",
   "nn": "30",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://zenodo.org/records/18606681",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Tech report claims a large gain in the hardest Runs N' Poses bin; no numeric page",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-openfold3",
   "benchmark": "bench-30-plinder",
   "nn": "30",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": "Runs N' Poses (protein-ligand)",
   "evidence_url": "https://portal.openfold.omsf.io/reports/of3p2_technical_report.pdf",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Runs N' Poses appears in a README bar chart; no numbers in text",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-pearl",
   "benchmark": "bench-30-plinder",
   "nn": "30",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": "Runs N' Poses, best@5 with PB-valid filter",
   "evidence_url": "https://arxiv.org/html/2510.24670v2",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Runs N' Poses best@5; baselines rerun by the Pearl authors",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-nesso-1",
   "benchmark": "bench-30-plinder",
   "nn": "30",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://www.valencelabs.com/wp-content/uploads/2026/07/nesso1.pdf",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "A missing candidate added and confirmed in the review",
   "resolution": "Third structural benchmark named in the same sentence, with the same metrics, baseline sourcing and filtering caveat; classed as a modified-protocol self-report.",
   "origin": "added (R7 missing candidate / review)"
  },
  {
   "model": "model-protenix",
   "benchmark": "bench-30-plinder",
   "nn": "30",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": "v1 self-report on the subset where all compared models have results (figure only)",
   "evidence_url": "https://arxiv.org/abs/2510.24670",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "v1 self-report on the subset where all models have results, figure only; plus a third-party figure in the Pearl paper",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-alphafold3",
   "benchmark": "bench-30-plinder",
   "nn": "30",
   "relation": "cited-as-comparison-only",
   "source_type": "third",
   "eval_set": "Runs N' Poses, best@5",
   "evidence_url": "https://arxiv.org/pdf/2510.24670",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Numbers quoted second-hand from the Pearl paper",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-boltz-1-1x",
   "benchmark": "bench-30-plinder",
   "nn": "30",
   "relation": "cited-as-comparison-only",
   "source_type": "third",
   "eval_set": "Runs N' Poses, best@5",
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "medium",
   "verification": "unverified",
   "note": "Numbers from the Pearl paper",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-boltz-2",
   "benchmark": "bench-30-plinder",
   "nn": "30",
   "relation": "cited-as-comparison-only",
   "source_type": "third",
   "eval_set": "Runs N' Poses",
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "medium",
   "verification": "unverified",
   "note": "Quoted in the Pearl paper and flagged not directly comparable; its official evaluation docs omit this benchmark",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-chai-1",
   "benchmark": "bench-30-plinder",
   "nn": "30",
   "relation": "cited-as-comparison-only",
   "source_type": "third",
   "eval_set": "Runs N' Poses, best@5",
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "medium",
   "verification": "unverified",
   "note": "Quoted from the Pearl paper",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-alphafold3",
   "benchmark": "bench-31-foldbench",
   "nn": "31",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "maintainer leaderboard",
   "evidence_url": "https://github.com/BEAM-Labs/FoldBench",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Maintainer leaderboard (FoldBench repo)",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-boltz-1-1x",
   "benchmark": "bench-31-foldbench",
   "nn": "31",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "maintainer leaderboard",
   "evidence_url": "https://github.com/BEAM-Labs/FoldBench",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "The maintainer board lists Boltz-1",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-boltz-2",
   "benchmark": "bench-31-foldbench",
   "nn": "31",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "maintainer run on post-2024-01 subset",
   "evidence_url": "https://github.com/BEAM-Labs/FoldBench",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Maintainer ran Boltz-2 on post-2024-01 subset (training cutoff later; reference only)",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-chai-1",
   "benchmark": "bench-31-foldbench",
   "nn": "31",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "maintainer leaderboard",
   "evidence_url": "https://github.com/BEAM-Labs/FoldBench",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Maintainer leaderboard",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-openfold3",
   "benchmark": "bench-31-foldbench",
   "nn": "31",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "maintainer leaderboard (preview)",
   "evidence_url": "https://github.com/BEAM-Labs/FoldBench",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Maintainer leaderboard (preview)",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-protenix",
   "benchmark": "bench-31-foldbench",
   "nn": "31",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "maintainer leaderboard",
   "evidence_url": "https://github.com/BEAM-Labs/FoldBench",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Maintainer leaderboard",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-rf3",
   "benchmark": "bench-31-foldbench",
   "nn": "31",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "maintainer leaderboard (2024-01+ subset)",
   "evidence_url": "https://github.com/BEAM-Labs/FoldBench",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Maintainer leaderboard (2024-01+ subset)",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-esmfold2",
   "benchmark": "bench-31-foldbench",
   "nn": "31",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": "FoldBench no-MSA complexes / antibody-antigen",
   "evidence_url": "https://biohub.org/news/world-model-of-protein-biology/",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Model-card figures are second-hand; another paper reports figures on its own antibody subset",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-intellifold-2",
   "benchmark": "bench-31-foldbench",
   "nn": "31",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": "FoldBench antibody-antigen / protein-ligand",
   "evidence_url": "https://doi.org/10.64898/2026.02.09.704787",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Published as a figure only; the predecessor reports numbers",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-seedfold",
   "benchmark": "bench-31-foldbench",
   "nn": "31",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": "FoldBench categories (protein-ligand, antibody-antigen, protein-protein, RNA)",
   "evidence_url": "https://arxiv.org/abs/2512.24354",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Self-reported on FoldBench; arXiv 2512.24354",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-nesso-1",
   "benchmark": "bench-31-foldbench",
   "nn": "31",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://www.valencelabs.com/wp-content/uploads/2026/07/nesso1.pdf",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Added by R7/fc_zero as a missing candidate and confirmed in the review.",
   "resolution": "Technical report names the benchmark and copies baselines from another paper while admitting its filtering criteria differ, so it is self-reported on a modified protocol, not an official entry. Moves this model off the zero-pairing list.",
   "origin": "added (R7 missing candidate / review)"
  },
  {
   "model": "model-opendde",
   "benchmark": "bench-31-foldbench",
   "nn": "31",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": "self-defined FoldBench antibody-antigen subset",
   "evidence_url": "https://arxiv.org/abs/2607.03787",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Self-defined FoldBench-AB antibody-antigen subset; not comparable to official board",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-tamgen",
   "benchmark": "bench-32-crossdocked",
   "nn": "32",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11522292/",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Self-reported on the 100 test pockets, with values in the supplement",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-alphafold3",
   "benchmark": "bench-33-posex",
   "nn": "33",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": "self-docking / cross-docking, benchmark authors' run",
   "evidence_url": "https://arxiv.org/html/2505.01700v3",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "PoseX authors ran AF3 under the same protocol (third party)",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-boltz-1-1x",
   "benchmark": "bench-33-posex",
   "nn": "33",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": "benchmark authors' own sets",
   "evidence_url": "https://arxiv.org/html/2505.01700v3",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "The benchmark paper's authors evaluated this model on their own sets.",
   "resolution": null,
   "origin": "added (R7 missing candidate)"
  },
  {
   "model": "model-chai-1",
   "benchmark": "bench-33-posex",
   "nn": "33",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": "benchmark authors' own sets",
   "evidence_url": "https://arxiv.org/html/2505.01700v3",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Same table as above.",
   "resolution": null,
   "origin": "added (R7 missing candidate)"
  },
  {
   "model": "model-diffdock",
   "benchmark": "bench-33-posex",
   "nn": "33",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": "PoseX, rerun by the benchmark authors",
   "evidence_url": "https://arxiv.org/html/2505.01700v3",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Evaluated by the benchmark paper.",
   "resolution": null,
   "origin": "added (R7 missing candidate)"
  },
  {
   "model": "model-protenix",
   "benchmark": "bench-33-posex",
   "nn": "33",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": "self-docking set, benchmark authors' run",
   "evidence_url": "https://arxiv.org/html/2505.01700v3",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "PoseX authors ran Protenix under the same protocol",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-vina",
   "benchmark": "bench-33-posex",
   "nn": "33",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": "PoseX subset, evaluated by the benchmark authors",
   "evidence_url": "https://arxiv.org/html/2505.01700v3",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Evaluated by the benchmark paper on its Astex subset.",
   "resolution": null,
   "origin": "added (R7 missing candidate)"
  },
  {
   "model": "model-alphafold3",
   "benchmark": "bench-34-abbibench",
   "nn": "34",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "registered interface-score entry",
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "medium",
   "verification": "unverified",
   "note": "Benchmark-registered ipSAE correlation (not structure accuracy), read from paper figure, not rerun",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-boltz-2",
   "benchmark": "bench-34-abbibench",
   "nn": "34",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "registered interface-score entry",
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "medium",
   "verification": "unverified",
   "note": "Benchmark-registered ipSAE entry; not structure accuracy",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-esm3",
   "benchmark": "bench-34-abbibench",
   "nn": "34",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "benchmark-registered entry",
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "medium",
   "verification": "unverified",
   "note": "Benchmark-registered score",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-esmfold2",
   "benchmark": "bench-34-abbibench",
   "nn": "34",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "AbBiBench structure-prediction entry",
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "medium",
   "verification": "unverified",
   "note": "Benchmark-registered ipSAE entry",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-prosst",
   "benchmark": "bench-34-abbibench",
   "nn": "34",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "antibody binding-affinity correlation, structure-aware LM category",
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "medium",
   "verification": "unverified",
   "note": "Benchmark-registered score",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-saprot",
   "benchmark": "bench-34-abbibench",
   "nn": "34",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "antibody binding-affinity correlation, structure-aware LM category",
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "medium",
   "verification": "unverified",
   "note": "Benchmark-registered score",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-chai-1",
   "benchmark": "bench-35-flab",
   "nn": "35",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": "zero-shot thermostability eval in the benchmark's own paper",
   "evidence_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12767642/",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "The FLAb2 paper evaluates this model zero-shot on thermostability; two site surfaces label the source type differently.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-iggm",
   "benchmark": "bench-36-aintibody",
   "nn": "36",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": null,
   "evidence_url": "https://github.com/TencentAI4S/IgGM",
   "evidence_site_page_only": false,
   "confidence": "low",
   "verification": "unverified",
   "note": "The team claims a top-three placement in the affinity-optimization task; no per-team standing is cited and official materials do not confirm it.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-opendde",
   "benchmark": "bench-36-aintibody",
   "nn": "36",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": "Challenge 1 (computational affinity maturation)",
   "evidence_url": "https://www.thailand-business-news.com/pr-news/nature-biotechnology-aureka-wins-the-global-blinded-ai-antibody-benchmark-ai-design-surpasses-the-best-experimental-result",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "disputed",
   "note": "The placement belongs to that company's internal model and cannot be credited to the open weights; the site matrix and model page disagree.",
   "resolution": "Ruled unconfirmed: the public weights cannot be matched to the competition entry.",
   "origin": "original-183"
  },
  {
   "model": "model-alphagenome",
   "benchmark": "bench-37-traitgym",
   "nn": "37",
   "relation": "self-reported-modified-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://doi.org/10.1038/s41586-025-10014-0",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Uses the variant set and matched controls but reports enrichment rather than AUPRC, so it is not board-comparable.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-borzoi",
   "benchmark": "bench-37-traitgym",
   "nn": "37",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": null,
   "evidence_url": "https://doi.org/10.1101/2025.02.11.637758",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Evaluated on this set by the benchmark's authors.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-evo-2",
   "benchmark": "bench-37-traitgym",
   "nn": "37",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": null,
   "evidence_url": "https://www.biorxiv.org/content/10.1101/2025.02.11.637758",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Evaluated on this set by the benchmark's authors.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-ribospan",
   "benchmark": "bench-39-rnagym",
   "nn": "39",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/pdf/2608.22849",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "The developer self-reports zero-shot results on this set's fitness task under its own aggregation.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-evo-2",
   "benchmark": "bench-39-rnagym",
   "nn": "39",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/pdf/2608.22849",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "disputed",
   "note": "The site matrix records a board entry while this page's figure is quoted via a third-party paper; the board entry awaits re-checking.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-esm3",
   "benchmark": "bench-40-motifbench",
   "nn": "40",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "MotifBench submission leaderboard (2025-05 submission)",
   "evidence_url": "https://github.com/blt2114/MotifBench",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "Entry on the MotifBench submission board (11.38, 2025-05).",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-la-proteina",
   "benchmark": "bench-40-motifbench",
   "nn": "40",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": null,
   "evidence_url": "https://github.com/blt2114/MotifBench",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "The board lists this model (29.75, 2026-07); the Chinese model page says there is no score, which is wrong.",
   "resolution": "The board lists La-Proteina (29.75, 2026-07), so the relation is official participation; the model page claiming no score is the error and must be fixed.",
   "origin": "original-183 (resolved)"
  },
  {
   "model": "model-rfdiffusion2-3",
   "benchmark": "bench-40-motifbench",
   "nn": "40",
   "relation": "official-participation",
   "source_type": "board",
   "eval_set": "official board entry (RFdiffusion3, 2026-08 snapshot)",
   "evidence_url": "https://github.com/blt2114/MotifBench",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "The board lists RFdiffusion3 (43.52, 2026-08); the Chinese model page says no entry was found, which is wrong.",
   "resolution": "The board and this record agree in listing RFdiffusion3 (43.52, 2026-08) as official participation; the Chinese model page must be fixed.",
   "origin": "original-183 (resolved)"
  },
  {
   "model": "model-biomni",
   "benchmark": "bench-41-bioml-bench",
   "nn": "41",
   "relation": "retrospective-dataset-use",
   "source_type": "third",
   "eval_set": null,
   "evidence_url": "https://www.biorxiv.org/content/10.1101/2025.09.01.673319",
   "evidence_site_page_only": false,
   "confidence": "medium",
   "verification": "partial",
   "note": "Re-run by the benchmark authors rather than reported by the developer; the Chinese matrix marks it self-reported, which under this round's definition should be third-party and is recorded as an open inconsistency.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-co-scientist",
   "benchmark": "bench-41-bioml-bench",
   "nn": "41",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/abs/2502.18864",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report on this benchmark found in official materials.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-gpt-rosalind",
   "benchmark": "bench-41-bioml-bench",
   "nn": "41",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report found; the only evidence is a site page, so it is shown as unconfirmed.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-intern-s",
   "benchmark": "bench-41-bioml-bench",
   "nn": "41",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://github.com/InternLM/Intern-S1",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report on this benchmark found in official materials.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-quine",
   "benchmark": "bench-41-bioml-bench",
   "nn": "41",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://www.microsoft.com/en-us/research/blog/introducing-quine-an-ai-research-system-designed-for-the-complexity-of-biology/",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report on this benchmark found in official materials.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-scireasoner",
   "benchmark": "bench-41-bioml-bench",
   "nn": "41",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "high",
   "verification": "disputed",
   "note": "The paper text does not mention this benchmark; the only evidence is a site page.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-verid",
   "benchmark": "bench-41-bioml-bench",
   "nn": "41",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report found; the only evidence is a site page, so it is shown as unconfirmed.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-frontier-llms",
   "benchmark": "bench-42-biomysterybench",
   "nn": "42",
   "relation": "self-reported-official-protocol",
   "source_type": "self",
   "eval_set": null,
   "evidence_url": "https://www.anthropic.com/research/Evaluating-Claude-For-Bioinformatics-With-BioMysteryBench",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "verified",
   "note": "The publisher runs the benchmark itself and reports scores; the cross-vendor board is run by a third party.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-co-scientist",
   "benchmark": "bench-42-biomysterybench",
   "nn": "42",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://arxiv.org/abs/2502.18864",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report on this benchmark found in official materials.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-gpt-rosalind",
   "benchmark": "bench-42-biomysterybench",
   "nn": "42",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report found; the only evidence is a site page, so it is shown as unconfirmed.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-intern-s",
   "benchmark": "bench-42-biomysterybench",
   "nn": "42",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://github.com/InternLM/Intern-S1",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report on this benchmark found in official materials.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-quine",
   "benchmark": "bench-42-biomysterybench",
   "nn": "42",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": "https://www.microsoft.com/en-us/research/blog/introducing-quine-an-ai-research-system-designed-for-the-complexity-of-biology/",
   "evidence_site_page_only": false,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report on this benchmark found in official materials.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-scireasoner",
   "benchmark": "bench-42-biomysterybench",
   "nn": "42",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "high",
   "verification": "disputed",
   "note": "The paper text does not mention this benchmark; the only evidence is a site page.",
   "resolution": null,
   "origin": "original-183"
  },
  {
   "model": "model-verid",
   "benchmark": "bench-42-biomysterybench",
   "nn": "42",
   "relation": "disputed-or-unconfirmed",
   "source_type": "unknown",
   "eval_set": null,
   "evidence_url": null,
   "evidence_site_page_only": true,
   "confidence": "high",
   "verification": "disputed",
   "note": "No report found; the only evidence is a site page, so it is shown as unconfirmed.",
   "resolution": null,
   "origin": "original-183"
  }
 ],
 "non_pairings": [
  {
   "model": "model-proteina-complexa",
   "nn": "40",
   "relation": "not-a-pairing",
   "note": "The method paper does not mention this benchmark; the earlier candidate list was wrong.",
   "evidence_url": "https://arxiv.org/abs/2603.27950",
   "confidence": "high",
   "source_type": "n/a"
  },
  {
   "model": "model-proteina-complexa",
   "nn": "30",
   "relation": "not-a-pairing",
   "note": "This benchmark family appears only as a protein-ligand training dataset, which is not a pairing.",
   "evidence_url": "https://arxiv.org/abs/2603.27950",
   "confidence": "high",
   "source_type": "n/a"
  },
  {
   "model": "model-evolvepro",
   "nn": "02",
   "relation": "not-a-pairing",
   "note": "12 DMS sets from the benchmark are used as a data source only; recorded explicitly as a non-pair so it is not re-added later.",
   "evidence_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11275896/",
   "confidence": "medium",
   "source_type": "n/a"
  },
  {
   "model": "model-boltzgen",
   "nn": "-",
   "relation": "not-a-pairing",
   "note": "No named public in-silico benchmark is reported in the manuscript, so the zero-pairing status stands.",
   "evidence_url": "withheld: author-hosted manuscript",
   "confidence": "high",
   "source_type": "n/a"
  },
  {
   "model": "model-lucaone",
   "nn": "-",
   "relation": "not-a-pairing",
   "note": "Tasks are bespoke; no named public suite on the site is reported. Third-party evaluations exist but on benchmarks that are not among the 44.",
   "evidence_url": "https://www.biorxiv.org/content/10.1101/2024.05.10.592927v2.full",
   "confidence": "high",
   "source_type": "n/a"
  }
 ],
 "zero_pairing": {
  "after": [
   {
    "model": "model-chai-2",
    "how_it_evaluates_itself": "{'wet-lab-validation': 2, 'comparison-vs-baseline-only': 1, 'own-task-set': 1, 'user-or-partner-report': 1} -> Antibody/nanobody wet-lab campaign; Miniprotein wet-lab test; Antibody-antigen folding (Chai-2f); Developability / polyreactivity; Full-length IgG update (2025-11)"
   },
   {
    "model": "model-amplify",
    "how_it_evaluates_itself": "{'comparison-vs-baseline-only': 2, 'own-task-set': 1, 'public-benchmark-not-on-site': 2} -> Held-out UniProt pseudo-perplexity; Masked-residue sequence recovery; Unsupervised contact prediction; Disorder discrimination; Inference throughput and design pipeline"
   },
   {
    "model": "model-evolvepro",
    "how_it_evaluates_itself": "{'own-task-set': 1, 'wet-lab-validation': 2} -> In silico DMS active-learning comparison; REGN10987 antibody engineering; PsaCas12f, PE2, Bxb1, T7 RNAP engineering"
   },
   {
    "model": "model-alphaproteo",
    "how_it_evaluates_itself": "{'wet-lab-validation': 1, 'comparison-vs-baseline-only': 1, 'case-study': 1} -> Seven-target binder wet-lab campaign; Success-rate comparison; Follow-on functional tests"
   },
   {
    "model": "model-latent-x2",
    "how_it_evaluates_itself": "{'wet-lab-validation': 2, 'own-task-set': 1, 'case-study': 1, 'user-or-partner-report': 1} -> Latent-X mini-binder / macrocycle campaign; Latent-X2 VHH/scFv campaign; Developability panel; Immunogenicity assay; Latent-Y agent campaigns"
   },
   {
    "model": "model-jam-2",
    "how_it_evaluates_itself": "{'wet-lab-validation': 3, 'comparison-vs-baseline-only': 1, 'case-study': 1} -> Target Set 1: 16 unseen targets; Head-to-head vs Chai-2 numbers; Epitope-directed set; GPCR native-cell binding; Experiment-guided steering"
   },
   {
    "model": "model-germinal",
    "how_it_evaluates_itself": "{'wet-lab-validation': 2, 'own-task-set': 1} -> Four-target nanobody campaign; Epitope check; Internal ablations"
   },
   {
    "model": "model-boltzgen",
    "how_it_evaluates_itself": "{'wet-lab-validation': 2, 'user-or-partner-report': 1, 'comparison-vs-baseline-only': 1} -> Novel-target wet-lab benchmark; Known-target check; Partner laboratory campaigns; Folding-model parity"
   },
   {
    "model": "model-enchant-v1-v2",
    "how_it_evaluates_itself": "{'public-benchmark-not-on-site': 1, 'comparison-vs-baseline-only': 1, 'own-task-set': 1} -> Obach human PK (half-life); Low-data Obach (5%); v2 internal sets"
   },
   {
    "model": "model-beacon",
    "how_it_evaluates_itself": "{'public-benchmark-not-on-site': 1, 'own-task-set': 1, 'user-or-partner-report': 1} -> OpenADMET challenges; Beacon-2 dose estimation; Partner fine-tuning"
   },
   {
    "model": "model-reinvent-4",
    "how_it_evaluates_itself": "No zero-evaluation record: evaluates itself only on its own task sets or has no public evaluation."
   },
   {
    "model": "model-saturn",
    "how_it_evaluates_itself": "{'own-task-set': 1, 'none-disclosed': 1} -> Docking MPO and Hit Ratio tasks; PMO"
   },
   {
    "model": "model-chemprop-v2",
    "how_it_evaluates_itself": "No zero-evaluation record: evaluates itself only on its own task sets or has no public evaluation."
   },
   {
    "model": "model-kermt",
    "how_it_evaluates_itself": "{'own-task-set': 2} -> Merck internal ADMET (30 endpoints); Public literature ADMET (25 endpoints) and Biogen set"
   },
   {
    "model": "model-transcriptformer",
    "how_it_evaluates_itself": "{'own-task-set': 3, 'case-study': 1} -> Cross-species cell-type classification; Spermatogenesis cross-species mapping; Human cell type and disease state; Gene-gene and TF analyses"
   },
   {
    "model": "model-robin",
    "how_it_evaluates_itself": "{'wet-lab-validation': 1, 'case-study': 1} -> Dry AMD lab-in-the-loop; Effect size conflict"
   },
   {
    "model": "model-txagent",
    "how_it_evaluates_itself": "{'own-task-set': 1, 'comparison-vs-baseline-only': 1} -> Five self-built benchmarks; Tool-use ablation"
   },
   {
    "model": "model-chai-3",
    "how_it_evaluates_itself": "{'none-disclosed': 1, 'user-or-partner-report': 1} -> Company statements; Pharma partnerships"
   },
   {
    "model": "model-helixfold-s1",
    "how_it_evaluates_itself": "{'own-task-set': 1, 'comparison-vs-baseline-only': 1} -> Self-built PDB interface sets; Sampling efficiency"
   },
   {
    "model": "model-bioemu-2",
    "how_it_evaluates_itself": "{'none-disclosed': 1} -> Model card evaluation areas"
   },
   {
    "model": "model-seedproteo",
    "how_it_evaluates_itself": "{'own-task-set': 2, 'wet-lab-validation': 1} -> Unconditional monomer generation; In silico binder design; SPR binding of designs"
   },
   {
    "model": "model-pinal",
    "how_it_evaluates_itself": "{'own-task-set': 1, 'wet-lab-validation': 3} -> Computational evaluation; Fluorescent protein; Metabolic H protein; PET hydrolase and alcohol dehydrogenase"
   },
   {
    "model": "model-dyno-psi",
    "how_it_evaluates_itself": "{'own-task-set': 1, 'wet-lab-validation': 1, 'comparison-vs-baseline-only': 1} -> In silico binder filter, 5 targets; IL-7RA yeast-display comparison; Press-release comparison"
   },
   {
    "model": "model-lucaone",
    "how_it_evaluates_itself": "{'own-task-set': 1, 'case-study': 1} -> 8 downstream validation tasks; Central-dogma few-shot analysis"
   },
   {
    "model": "model-rfantibody",
    "how_it_evaluates_itself": "{'wet-lab-validation': 4} -> Yeast display of VHH designs; Affinity maturation (OrthoRep); Cryo-EM validation; scFv and full-length IgG designs"
   },
   {
    "model": "model-tfold",
    "how_it_evaluates_itself": "{'own-task-set': 3, 'wet-lab-validation': 1} -> SAbDab-22H2-Ab structure test (n=169); SAbDab-22H2-AbAg (n=99); Virtual screening; De novo design, 4 targets"
   },
   {
    "model": "model-hcablm",
    "how_it_evaluates_itself": "{'own-task-set': 2, 'comparison-vs-baseline-only': 1} -> Sequence distribution analysis; Frozen-embedding transfer; Press-release baseline claim"
   },
   {
    "model": "model-origin-1",
    "how_it_evaluates_itself": "{'comparison-vs-baseline-only': 1, 'own-task-set': 1, 'wet-lab-validation': 2} -> In silico comparison vs RFantibody; AbsciBind discrimination; Zero-prior epitope design, 10 targets; IL36RA affinity maturation"
   },
   {
    "model": "model-aido-cell",
    "how_it_evaluates_itself": "No zero-evaluation record: evaluates itself only on its own task sets or has no public evaluation."
   },
   {
    "model": "model-bulkformer",
    "how_it_evaluates_itself": "{'own-task-set': 1} -> Six downstream tasks (preprint)"
   },
   {
    "model": "model-scprint-2",
    "how_it_evaluates_itself": "No zero-evaluation record: evaluates itself only on its own task sets or has no public evaluation."
   },
   {
    "model": "model-co-scientist",
    "how_it_evaluates_itself": "{'public-benchmark-not-on-site': 1, 'user-or-partner-report': 1, 'wet-lab-validation': 1, 'own-task-set': 1} -> Elo self-rating vs GPQA Diamond; Expert evaluation of hypotheses; Collaborator case studies with wet lab; Elo tournament"
   },
   {
    "model": "model-verid",
    "how_it_evaluates_itself": "{'case-study': 1, 'wet-lab-validation': 2} -> Digital-twin protocol cases; Aptamer design loops; Epitope excision FAP binders"
   },
   {
    "model": "model-quine",
    "how_it_evaluates_itself": "{'wet-lab-validation': 1, 'none-disclosed': 1} -> PDAC cell-state transition prediction; Benchmarks"
   },
   {
    "model": "model-intern-s",
    "how_it_evaluates_itself": "{'public-benchmark-not-on-site': 2, 'own-task-set': 1} -> Biology-Instructions / Mol-Instructions; ProteinLMBench, MicroVQA, ChemBench, MolecularIQ, SciReasoner; ProteinBinder-9"
   }
  ],
  "left_the_list": [
   "model-af2-multimer",
   "model-dplm-2",
   "model-nesso-1",
   "model-proteina-complexa"
  ],
  "joined_the_list": [
   "model-aido-cell",
   "model-chemprop-v2",
   "model-reinvent-4",
   "model-scprint-2"
  ]
 }
}
