Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Mathematical Reasoning on Math-MC (test)

58.04Accuracy

CORAL

23.179232.229641.2850.3304Feb 5, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
58.043.223.0663.3121.89
2026.02
56.785.123.1964.4922.09
2026.02
55.7422.583.7180.5729.32
2026.02
45.653.22.7865.4223.12
2026.02
44.8920.168.6791.5529.38
2026.02
44.434.572.45105.1337.51
2026.02
43.736.463.3766.2123.47
2026.02
39.9513.116.0273.6425.71
2026.02
39.9340.933.58111.6141.08
2026.02
38.2811.154.3171.6227.89
2026.02
34.8519.2913.55110.4438.76
2026.02
30.2743.911.72101.6737.09
2026.02
27.5575.9436.83156.7751.56
2026.02
26.9428.558.1481.7832.46
2026.02
24.5249.3925.57126.145.12