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

Mathematical Reasoning on AIME 2026 (accuracy)

93.3AIME 2026 Accuracy

SU-01

-1.02823.46147.9572.439Apr 28, 2026May 1, 2026May 5, 2026May 9, 2026May 12, 2026May 16, 2026May 20, 2026
Updated 12d ago

Evaluation Results

MethodLinks
2026.05
93.3
2026.05
92.9
2026.05
91.3
2026.05
90
2026.05
89.6
2026.05
88.3
2026.04
86.7
2026.05
79.7
2026.04
76.7
2026.04
76.7
2026.05
75.2
2026.05
75.1
2026.04
73.3
2026.04
73.3
2026.05
70.8
2026.05
64.9
2026.05
64.7
2026.04
63.3
2026.04
63.3
2026.05
62.2
2026.05
57.8
2026.05
56.8
2026.05
54.3
2026.05
48.65
2026.05
46.7
2026.05
45.21
2026.05
44.27
2026.05
42.5
2026.05
41.46
2026.05
41.46
2026.05
40.73
2026.05
39.79
2026.05
39.17
2026.05
33.23
2026.05
28.12
2026.05
26.77
2026.05
26.46
2026.05
26.25
2026.05
24.17
2026.05
23.96
2026.05
20.97
2026.05
19.06
2026.05
18.85
2026.05
18.43
2026.05
18.02
2026.05
17.8
2026.05
15.1
2026.05
12.71
2026.05
12.3
2026.05
10.73
2026.05
9.3
2026.05
9.3
2026.05
9
2026.05
5.3
2026.05
2.6