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

Mathematical Reasoning on AIME 2024 (Accuracy %)

62.9AIME 2024 Accuracy

Base

-2.51614.46731.4548.433May 16, 2026May 17, 2026May 19, 2026May 20, 2026May 22, 2026May 23, 2026May 25, 2026
Updated 7d ago

Evaluation Results

MethodLinks
2026.05
62.9
2026.05
59.86
2026.05
57.71
2026.05
56.9
2026.05
56.35
2026.05
55
2026.05
54.17
2026.05
54.15
2026.05
54.05
2026.05
53.56
2026.05
53.46
2026.05
52.7
2026.05
51.88
2026.05
51.56
2026.05
51.5
2026.05
51.25
2026.05
48.33
2026.05
48.02
2026.05
44.4
2026.05
39.89
2026.05
36.04
2026.05
32.1
2026.05
29
2026.05
26
2026.05
24.2
2026.05
17.5
2026.05
15
2026.05
12.3
2026.05
11
2026.05
9.4
2026.05
6.7
2026.05
4.8
2026.05
2.3
2026.05
1.9
2026.05
0.4
2026.05
0
2026.05
0