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

General Reasoning on Overall MATH-500 AIME25 HumanEval GPQA

85.1Accuracy

Vanilla

49.53258.7666877.234Mar 13, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
85.1100
2026.03
83.4100
2026.03
79.973.9
2026.03
7865
2026.03
77.4100
2026.03
77100
2026.03
76.975.1
2026.03
76.565
2026.03
73.464.7
2026.03
72.667.8
2026.03
70.683.1
2026.03
70.186.8
2026.03
68.878.9
2026.03
67.751.6
2026.03
66.584.5
2026.03
62.249.2
2026.03
59.678
2026.03
59.314.6
2026.03
57.375.8
2026.03
5686.5
2026.03
55.217.1
2026.03
55.213.7
2026.03
5315.6
2026.03
50.975.3