{ "base": { "math500": 0.66, "darija_mmlu": 0.345, "identity": 0.0, "humaneval": 0.9390243902439024 }, "previous": { "livecodebench": 0.475, "livecodebench/easy": 0.9523809523809523, "livecodebench/hard": 0.16666666666666666, "livecodebench/medium": 0.5217391304347826, "gpqa_diamond": 0.6060606060606061, "gpqa/biology": 0.42105263157894735, "gpqa/chemistry": 0.41935483870967744, "gpqa/physics": 0.8488372093023255, "aime2025": 0.6208333333333333, "aime/algebra": 0.7222222222222222, "aime/combinatorics": 0.5416666666666666, "aime/geometry": 0.6607142857142857, "aime/number theory": 0.525, "darija_mmlu": 0.64, "identity": 0.9375 }, "svl20": { "livecodebench": 0.4875, "livecodebench/easy": 0.9523809523809523, "livecodebench/hard": 0.1388888888888889, "livecodebench/medium": 0.6086956521739131, "gpqa_diamond": 0.6212121212121212, "gpqa/biology": 0.5263157894736842, "gpqa/chemistry": 0.3870967741935484, "gpqa/physics": 0.8953488372093024, "aime2025": 0.6166666666666667, "aime/algebra": 0.5972222222222222, "aime/combinatorics": 0.5277777777777778, "aime/geometry": 0.8392857142857143, "aime/number theory": 0.5, "darija_mmlu": 0.6425, "identity": 0.9375 } }