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

Mathematical Reasoning on MPMath

79.77Accuracy

Qwen2.5(14B)T

35.185246.760158.33569.9099Jul 4, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2026.07
79.77-
2026.07
78.86-
2026.07
42.915.58
2026.07
42.885.5
2026.07
38.911.58
2026.07
38.911.53
2026.07
37.380
2026.07
37.330
2026.07
37.28-0.1
2026.07
37.26-0.07
2026.07
36.9-0.43