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

Mathematical Reasoning on MATH 500 (Accuracy Avg@8)

89.05Accuracy (Avg@8)

L1-Qwen-7B-Max

66.11872.071578.02583.9785May 28, 2026
Updated 5d ago

Evaluation Results

MethodLinks
2026.05
89.05
2026.05
88.4
2026.05
87.45
2026.05
86.5
2026.05
85.35
2026.05
72.53
2026.05
71.95
2026.05
70.1
2026.05
69.25
2026.05
67