{"schema_version":1,"total":1,"offset":0,"limit":100,"observations":[{"id":"public:3f75786ce0f3b9ede0efd924","benchmark_id":"ugi-willingness::snapshot-2026-09-10","subject":{"source_id":"mistralai/Devstral-Small-2-24B-Instruct-2512","name":"mistralai/Devstral-Small-2-24B-Instruct-2512","model_id":"devstral-small-2::default","variant":null,"harness":null},"value":6.8,"unit":"points","basis":"measured","source":{"url":"https://huggingface.co/spaces/DontPlanToEnd/UGI-Leaderboard/raw/main/ugi-leaderboard-data.csv","retrieved_at":"2026-09-10T22:04:13Z","published_at":null,"file":"ops/rebuild-2026-09/evidence/phase-04/sources/supp-6c45283c6461.gz","sha256":"4154635c4557af4b4eebbeaab6970bdf8296aef44e46f6193fdb4976cd8fe7f2","locator":"csv; source row 746; mistralai/Devstral-Small-2-24B-Instruct-2512; field W/10 👍"},"protocol":"W/10 👍 published composite; Prompt Template=mistral V7-Tekken; Test Date=12/13/2025; Model Link=https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512; Is Thinking Model=False","comparison_key":null,"join_note":"Unique exact Hugging Face checkpoint URL in retained catalog metadata; source effort remains as published."}],"divergences":[],"cell":null,"coverage":{"model":null,"benchmark":{"total_models":844,"available":74,"unknown":770,"not_tested":0,"not_published":0,"source_unreachable":0,"contested":0,"measured":74,"self_reported":0,"observations":1309,"unmatched_observations":1235}},"collection":{"benchmark_id":"ugi-willingness::snapshot-2026-09-10","status":"collected","source_url":"https://huggingface.co/spaces/DontPlanToEnd/UGI-Leaderboard/raw/main/ugi-leaderboard-data.csv","reason":"1309 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."}