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

Math Reasoning on BeyondBench Easy

96.67Accuracy

EFFGEN

33.552449.938766.32582.7113Jan 31, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.01
96.67
2026.01
94.63
2026.01
92.44
2026.01
92.27
2026.01
89.02
2026.01
88.05
2026.01
86.27
2026.01
81.71
2026.01
80.24
2026.01
77.8
2026.01
77.07
2026.01
74.71
2026.01
73.66
2026.01
72.2
2026.01
71.56
2026.01
64.63
2026.01
63.41
2026.01
59.68
2026.01
58.78
2026.01
56.39
2026.01
52.95
2026.01
52.68
2026.01
49.39
2026.01
42.05
2026.01
35.98