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

Mathematical Reasoning on AMC (Acc@8, Pass@8)

79.52Acc@8

DiPO

3.714423.394743.07562.7553Mar 10, 2026Mar 16, 2026Mar 22, 2026Mar 28, 2026Apr 3, 2026Apr 9, 2026Apr 15, 2026
Updated 2d ago

Evaluation Results

MethodLinks
2026.04
79.52-
2026.04
78.31-
2026.04
77.11-
2026.04
77.11-
2026.04
75.9-
2026.04
72.29-
2026.04
69.88-
2026.04
69.88-
2026.04
68.67-
2026.04
68.67-
2026.04
67.47-
2026.04
67.47-
2026.04
65.06-
2026.04
63.86-
2026.04
63.86-
2026.04
59.04-
2026.04
46.99-
2026.04
27.71-
2026.03
23.3454.22
2026.03
22.2944.58
2026.03
20.7846.98
2026.03
20.4844.58
2026.03
19.5839.76
2026.03
18.6733.73
2026.03
17.7737.35
2026.03
12.6527.71
2026.03
6.6331.32