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

Mathematical Reasoning on MATH 500 (Accuracy Statistics)

66.72Mean Accuracy (MATH 500)

KTO

45.628851.104456.5862.0556Jun 8, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
66.720.5866
2026.06
63.682.0161.19
2026.06
63.641.362.03
2026.06
612.7657.57
2026.06
60.681.1959.2
2026.06
59.921.5258.03
2026.06
57.21.8354.93
2026.06
54.640.753.77
2026.06
53.21.0251.93
2026.06
52.841.3151.22
2026.06
51.841.4650.03
2026.06
49.40.7348.49
2026.06
47.961.7345.81
2026.06
46.442.0443.91