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

Math Reasoning on BeyondBench Easy

96.67Accuracy

EFFGEN

33.552449.938766.32582.7113Jan 31, 2026
Updated 1mo 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