Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Math Reasoning on BeyondBench Hard

58.86Accuracy

EFFGEN

-0.867214.638930.14545.6511Jan 31, 2026
Updated 4d 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