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

Mathematical Reasoning on AIME 24/25 (Acc, Ent)

71.88Accuracy

Policy Split

33.86843.736553.60563.4735Apr 13, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.04
71.880.55
2026.04
71.670.49
2026.04
71.060.48
2026.04
70.830.35
2026.04
70.620.51
2026.04
70.290.36
2026.04
69.790.58
2026.04
69.580.35
2026.04
69.170.35
2026.04
68.870.35
2026.04
68.830.53
2026.04
68.120.73
2026.04
67.290.4
2026.04
67.290.4
2026.04
67.080.39
2026.04
67.080.39
2026.04
66.040.4
2026.04
65.880.73
2026.04
43.250.68
2026.04
42.920.74
2026.04
42.290.64
2026.04
41.040.35
2026.04
40.540.36
2026.04
38.330.36
2026.04
37.920.36
2026.04
36.460.36
2026.04
35.330.78