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

Mathematical Reasoning on AIME 24 (P@8, P@4, P@1)

86.67P@8

MOTAB

45.0755.8766.6777.47May 19, 2026
Updated 14d ago

Evaluation Results

MethodLinks
2026.05
86.6778.3347.08
2026.05
83.3375.2946.66
2026.05
8074.5745.83
2026.05
8073.1436.25
2026.05
76.6773.1443.33
2026.05
76.6772.2944.17
2026.05
66.6757.5734.17
2026.05
56.6743.3327.5
2026.05
53.334525
2026.05
53.3348.3324.17
2026.05
5037.8121.25
2026.05
46.6738.3821.67
2026.05
46.6740.7124.17