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

Mathematical Reasoning on AMC 2023 (avg@16)

89.8Avg@16 Score

NSR (Weighted-Reinforce)

-2.13621.73245.669.468Mar 19, 2026Mar 26, 2026Apr 2, 2026Apr 9, 2026Apr 16, 2026Apr 23, 2026May 1, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.05
89.8
2026.05
89.7
2026.05
89.6
2026.05
89.4
2026.05
87.2
2026.05
85.8
2026.05
85.8
2026.05
79.8
2026.05
78
2026.05
74.5
2026.05
71.3
2026.05
66.9
2026.05
66.7
2026.03
65.9
2026.03
63.4
2026.03
63.4
2026.05
63.4
2026.05
61.4
2026.03
60.3
2026.03
60.2
2026.03
58.8
2026.05
58.4
2026.03
57.5
2026.05
57.5
2026.05
56.9
2026.05
54.2
2026.03
53.3
2026.03
49.5
2026.03
49.5
2026.03
49.4
2026.03
48.9
2026.03
47.7
2026.03
47
2026.03
46.2
2026.05
43.9
2026.03
34.5
2026.03
28.8
2026.03
28.4
2026.03
27.3
2026.03
25
2026.03
24.8
2026.03
23.8
2026.03
22.3
2026.03
21.9
2026.03
18.8
2026.03
13.6
2026.03
7.5
2026.03
1.4