{"schema_version":1,"total":1,"offset":0,"limit":100,"observations":[{"id":"aa:e9a09db3-8fd6-41dd-ba2f-20e0a2bff7f2:gdpval","benchmark_id":"aa-gdpval::2","subject":{"source_id":"e9a09db3-8fd6-41dd-ba2f-20e0a2bff7f2","name":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort)","model_id":"claude-opus-4.7::max","variant":"max","harness":null},"value":1395.78,"unit":"Elo","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 e9a09db3-8fd6-41dd-ba2f-20e0a2bff7f2; gdpval"},"protocol":"Bradley-Terry Elo from pairwise judge-panel comparisons, human experts anchored at 1000; AA methodology captured 2026-09-10; effort max","comparison_key":null}],"divergences":[],"cell":null,"coverage":{"model":null,"benchmark":{"total_models":835,"available":239,"unknown":596,"not_tested":0,"not_published":0,"source_unreachable":0,"contested":0,"measured":239,"self_reported":0,"observations":241,"unmatched_observations":2}},"collection":{"benchmark_id":"aa-gdpval::2","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. Basis counts count covered cells, not runs; measured and self_reported may overlap. Unmatched source identities remain in observations and never inflate catalog coverage."}