{"schema_version":1,"total":1,"offset":0,"limit":100,"observations":[{"id":"public:0079b58b6104de058e094d67","benchmark_id":"livebench::2026-06-25","subject":{"source_id":"minimax-m3","name":"minimax-m3","model_id":"minimax-m3::default","variant":null,"harness":null},"value":67.26,"unit":"points","basis":"derived","source":{"url":"https://livebench.ai/table_2026_06_25.csv","retrieved_at":"2026-09-10T22:23:14Z","published_at":null,"file":"ops/rebuild-2026-09/evidence/phase-04/sources/final-e70f40005b36.gz","sha256":"186ca65e7bb3a07aa26875eb3c45bfbe4e22d1ef36165cdaa11ad1a58087817c","locator":"livebench; source row 21; minimax-m3; field value"},"protocol":"Release 2026-06-25; seven category means with equal category weights, published 2-decimal overall and explicit Grok-3 exceptions. Complete task scores required.","comparison_key":null,"source_basis":"measured","derivation":{"formula":"Mean of seven category means, rounded to the published 2 decimals; source Grok-3 Thinking=72 and Grok-3=58 overrides retained.","inputs":[76.923,61,94,66,69.014,67.391,63.636,23.333,35,75,56,91.176,85.614,84.614,45.846,98.039,96.333,50.174,84,55.933,56.617,63.55,53.933]},"supporting_sources":[{"url":"https://livebench.ai/categories_2026_06_25.json","file":"ops/rebuild-2026-09/evidence/phase-04/sources/final-8fb1bd6bc30b.gz","sha256":"dad300ad18655b69db720e1b88fc5a5eac06c5b2f0e52c2bf50f10ff057674f3","retrieved_at":"2026-09-10T22:23:16Z","published_at":null,"locator":"categories_source"},{"url":"https://livebench.ai/static/js/main.04358d6f.js","file":"data/raw/benchmarks/daily-evidence/2026-09-21-livebench/b29cff6f2cd542927e75.gz","sha256":"b29cff6f2cd542927e75c9a582f65c4e8d290fb8dd244387d2f85969bdd003aa","retrieved_at":"2026-09-21T02:05:35.724575+00:00","published_at":null,"locator":"frontend_source"}],"join_note":"Reviewed identity map 2026-09-20: label names minimax-m3 without a setting; the catalog has exactly one configuration, the default (minimax-m3::default)"}],"divergences":[],"cell":null,"coverage":{"model":null,"benchmark":{"total_models":924,"available":36,"unknown":888,"not_tested":0,"not_published":0,"source_unreachable":0,"contested":0,"measured":36,"self_reported":0,"observations":63,"unmatched_observations":27}},"collection":{"benchmark_id":"livebench::2026-06-25","status":"collected","source_url":"https://livebench.ai/table_2026_06_25.csv","reason":"57 source results parsed; configurations remain separate; unmatched model identities are retained."},"coverage_note":"Denominators are catalog model configurations × versioned registry entries; capability_available excludes Efficiency (cost) boards. Basis counts count covered cells, not runs; measured and self_reported may overlap. Unmatched source identities remain in observations and never inflate catalog coverage."}