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

Mathematical Reasoning on MATH (Accuracy, Delta Avg)

92.8Accuracy

CoT2-Meta

5.4428.1250.873.48Jul 4, 2025Aug 17, 2025Oct 1, 2025Nov 15, 2025Dec 30, 2025Feb 13, 2026Mar 30, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
92.814.5
2026.03
87.48.3
2026.03
84.24.8
2026.03
84.210.5
2026.03
78.65.7
2026.03
78.5-
2026.03
75.33
2026.03
70.8-
2026.03
64.212.2
2026.03
59.16.4
2026.03
55.83.4
2026.03
50.4-
2025.07
14.3-
2025.07
12.6-
2025.07
12.5-
2025.07
8.8-