{"schema_version":1,"total":1,"offset":0,"limit":100,"observations":[{"id":"public:fc8754ca00235bc94128bcf6","benchmark_id":"lisanbench::0.2.0","subject":{"source_id":"kimi-k3:thinking-max","name":"Kimi K3 (max)","model_id":"kimi-k3::max","variant":null,"harness":null},"value":10520.67,"unit":"points","basis":"measured","source":{"url":"https://lisanbench.com/data/core.json","retrieved_at":"2026-09-16T19:06:45.428158+00:00","published_at":null,"file":"data/raw/benchmarks/daily-evidence/2026-09-16-lisanbench/09ce01d262ad08e01228.gz","sha256":"09ce01d262ad08e012282fc2286890f489691a0facc1afd3cb4ef2acd801b339","locator":"lisanbench_core; source row 150; kimi-k3:thinking-max; field path_length"},"protocol":"LisanBench v0.2.0 (Lisan al Gaib): 50 pinned starting words, pinned SCOWL 2026-02-25 dictionary, Levenshtein distance 1, no repeats; path length = valid transitions in the longest valid prefix, averaged over the model's trials per word and summed over the 50 words, as published; the maintainer's API route and the listed trial count are recorded per row; not a Composite input.; source row: {\"model\":\"kimi-k3:thinking-max\",\"route\":\"moonshotai/kimi-k3:thinking-max\",\"label\":\"Kimi K3 (max)\",\"company\":\"other\",\"thinking\":true,\"trials_total\":150,\"trials_per_word\":[3,3],\"difficulty_weighted_score\":3525.7707,\"best_trial_sum\":15715.0,\"average_validity\":0.9965,\"output_tokens\":4220627,\"estimated_run_cost_usd\":63.480063,\"model_release_date\":\"2026-07-15\"}","comparison_key":null,"supporting_sources":[{"url":"https://raw.githubusercontent.com/voice-from-the-outer-world/lisan-bench/main/README.md","file":"data/raw/benchmarks/daily-evidence/2026-09-16-lisanbench/1ee21c293a38f88cb7c2.gz","sha256":"1ee21c293a38f88cb7c2135d2205d97ee6f6620a1982be1320d8a4c7fe2a50b0","retrieved_at":"2026-09-16T19:06:53.678641+00:00","published_at":null,"locator":"method_source"},{"url":"https://lisanbench.com/data/rankings.json","file":"data/raw/benchmarks/daily-evidence/2026-09-16-lisanbench/6d97496b0853e1f2a2af.gz","sha256":"6d97496b0853e1f2a2af91076243759624a09080f7b6e75ad0106471e4b18ce2","retrieved_at":"2026-09-16T19:06:48.201893+00:00","published_at":null,"locator":"detail_source"}],"join_note":"Reviewed identity map 2026-09-16: label states model kimi-k3 and setting max; exact catalog configuration kimi-k3::max"}],"divergences":[],"cell":null,"coverage":{"model":null,"benchmark":{"total_models":924,"available":52,"unknown":872,"not_tested":0,"not_published":0,"source_unreachable":0,"contested":0,"measured":52,"self_reported":0,"observations":154,"unmatched_observations":102}},"collection":{"benchmark_id":"lisanbench::0.2.0","status":"collected","source_url":"https://lisanbench.com/data/core.json","reason":"154 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."}