{"schema_version":1,"total":1,"offset":0,"limit":100,"observations":[{"id":"aa:1b05e346-e86a-4a20-8feb-7da8c65a99aa:aime25","benchmark_id":"aa-aime::2025","subject":{"source_id":"1b05e346-e86a-4a20-8feb-7da8c65a99aa","name":"Mistral Large 2 (Jul '24)","model_id":"mistral-large-2-jul-24::default","variant":null,"harness":null},"value":0,"unit":"fraction","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 1b05e346-e86a-4a20-8feb-7da8c65a99aa; aime25"},"protocol":"Pass@1 correctness averaged over ten repeats; AA methodology captured 2026-09-19; effort not in effort field (exact UUID retained)","comparison_key":null}],"divergences":[],"cell":null,"coverage":{"model":null,"benchmark":{"total_models":844,"available":270,"unknown":574,"not_tested":0,"not_published":0,"source_unreachable":0,"contested":0,"measured":270,"self_reported":0,"observations":270,"unmatched_observations":0}},"collection":{"benchmark_id":"aa-aime::2025","status":"collected","source_url":"https://artificialanalysis.ai/models/gpt-5-6-sol","reason":"Exact AA UUID and field from the reviewed protocol snapshot; null does not prove whether AA ran the test."},"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."}