Mathematical Reasoning on MATH (Accuracy, Number of samples)
76.1AccuracyCPDAA
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CPDAAModel=Average across models2026.04 | 76.1 | 8.3 | |
| CPFFModel=Average across models2026.04 | 76 | 12.6 | |
| CPAAModel=Average across models2026.04 | 75.8 | 8.1 | |
| CPDFAModel=Average across models2026.04 | 75.8 | 10.4 | |
| CPFAModel=Average across models2026.04 | 75.6 | 9.8 | |
| ASCModel=Average across models2026.04 | 74.2 | 12.6 | |
| ESCModel=Average across models2026.04 | 74.1 | 16.4 |