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

Math Reasoning on BeyondBench Hard

58.86Accuracy

EFFGEN

-0.867214.638930.14545.6511Jan 31, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
58.86
2026.01
46.37
2026.01
45.83
2026.01
34.29
2026.01
30.67
2026.01
29.58
2026.01
28.57
2026.01
27.14
2026.01
26.53
2026.01
24.29
2026.01
24.17
2026.01
24.17
2026.01
21.67
2026.01
15.42
2026.01
12.86
2026.01
8.57
2026.01
7.92
2026.01
7.33
2026.01
7.14
2026.01
7.14
2026.01
5.71
2026.01
2.86
2026.01
1.67
2026.01
1.43
2026.01
1.43