{ "model": "runs/v3b", "quant": null, "agreement": { "rows": 5125, "agree": 0.6874146341463415, "kl": 0.6401720955939848, "brier": 0.28186191172584546, "per_file": { "data/eval_mmlu_pro_think512.jsonl": { "rows": 1999, "agree": 0.49024512256128067, "kl": 1.345718805884049, "brier": 0.5798118903688055 }, "data/eval_wide.jsonl": { "rows": 920, "agree": 0.8521739130434782, "kl": 0.24507102074775225, "brier": 0.09771515623017962 }, "data/eval_xnli.jsonl": { "rows": 740, "agree": 0.8405405405405405, "kl": 0.12840145847645495, "brier": 0.07536055317105994 }, "data/eval_multi.jsonl": { "rows": 1466, "agree": 0.7755798090040927, "kl": 0.18438450108898327, "brier": 0.09538443087951312 } } }, "mmlu_pro": { "rows": 2000, "accuracy": 0.4195 }, "latency": [ { "questions": 1, "p50_ms": 27.914823964238167, "p99_ms": 28.93548645079136 }, { "questions": 10, "p50_ms": 47.78458643704653, "p99_ms": 48.7666130065918 } ] }