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

Mathematical Reasoning on MATH 500 (Pass@1, Avg Response Length)

94.2Pass@1 Accuracy

ExpThink

77.97682.18886.490.612May 8, 2026
Updated 23d ago

Evaluation Results

MethodLinks
2026.05
94.2755.7
2026.05
935,315.2
2026.05
92.41,253
2026.05
91.61,868.2
2026.05
91.32,109.8
2026.05
911,752.2
2026.05
90.82,971.1
2026.05
89.83,723.8
2026.05
891,529.3
2026.05
84.62,602.7
2026.05
83.81,851.1
2026.05
82.83,179.6
2026.05
82.21,417
2026.05
814,635.5
2026.05
79.82,358.3
2026.05
78.62,257.1