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

Mathematical Reasoning on AIME 2025 (Accuracy)

91.67Accuracy

HEART

-2.210822.162146.53570.9079Jun 4, 2025Jul 19, 2025Sep 2, 2025Oct 17, 2025Dec 1, 2025Jan 15, 2026Mar 2, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2025.09
91.67
2025.09
90.83
2026.03
88.7
2025.09
88.33
86.7
2026.03
81.5
2026.03
79.6
79.2
2026.03
78.2
2026.03
74.8
2026.03
74.4
2026.03
72.9
2026.03
72.5
2026.03
70
2025.12
63.3
2025.12
56.7
2025.12
54.6
2025.09
52.5
2025.09
50.83
2025.12
50
2025.12
47.5
2025.12
45.8
2025.12
45.4
2025.12
45
2025.09
40
2025.12
40
2025.06
40
2025.09
36.9
2025.09
35
2025.12
35
2025.06
33
2025.06
33
2025.06
33
2025.12
31.7
2025.12
31.3
2025.12
30
2025.06
27
2025.12
26.7
2025.12
26.7
2025.12
25.8
2025.06
23
2026.03
20.1
2026.03
18.2
2025.12
17.9
2025.12
15
2025.09
12.9
2025.09
12.1
2025.12
10.8
2025.06
10
2025.12
8.8
2025.09
8.3
2025.09
7.7
2025.06
7
2025.12
6.7
2025.12
5
2025.06
3
2025.12
1.7
2025.09
1.5
2025.09
1.4