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

Mathematical Reasoning on AIME 2024 (mean@8)

68.3Mean Score (k=8)

SD-ZERO

-2.73215.70934.1552.591Mar 11, 2026Mar 16, 2026Mar 22, 2026Mar 27, 2026Apr 2, 2026Apr 7, 2026Apr 13, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2026.04
68.3
2026.04
66.7
2026.04
64.2
2026.04
63.3
2026.04
62.5
2026.04
61.7
2026.04
61.7
2026.04
59.6
2026.04
59.2
2026.04
56.7
2026.04
56.7
2026.04
54.6
2026.04
52.9
2026.04
51.3
2026.04
38.8
2026.04
37.9
2026.04
33.8
2026.03
31.6
2026.03
28.9
2026.03
28.2
2026.04
27.5
2026.04
27.1
2026.03
25.3
2026.03
19.6
2026.04
19.6
2026.04
19.2
2026.04
19.2
2026.04
18.8
2026.04
17.9
2026.04
17.9
2026.04
17.5
2026.04
16.7
2026.04
16.2
2026.04
15
2026.04
14.2
2026.04
13.8
2026.04
11.7
2026.04
11.7
2026.04
11.7
2026.04
10.8
2026.04
10.4
2026.04
10
2026.04
5.4
2026.04
2.9
2026.04
2.1
2026.04
1.2
2026.04
0.8
2026.04
0.4
2026.04
0.4
2026.04
0
2026.04
0
2026.04
0
2026.04
0
2026.04
0
2026.04
0
2026.04
0
2026.04
0
2026.04
0
2026.04
0