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

Reasoning on AIME 2025 (Pass@1)

67.66Pass@1

FP16

23.782435.173746.56557.9563May 9, 2026
Updated 22d ago

Evaluation Results

MethodLinks
2026.05
67.66
2026.05
66.98
2026.05
65.21
2026.05
64.52
2026.05
64.27
2026.05
63.75
2026.05
62.66
2026.05
61.72
2026.05
60.78
2026.05
59.48
2026.05
58.67
2026.05
57.66
2026.05
35.94
2026.05
35.47
2026.05
32.71
2026.05
32.55
2026.05
31.77
2026.05
31.2
2026.05
29.85
2026.05
29.53
2026.05
28.54
2026.05
27.6
2026.05
27.29
2026.05
25.47