Mathematical Reasoning on SVAMP (Accuracy, Number of samples)
95.6AccuracyCPFF
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CPFFModel=Average across models2026.04 | 95.6 | 3.3 | |
| CPDFAModel=Average across models2026.04 | 95.5 | 2.8 | |
| CPFAModel=Average across models2026.04 | 95.3 | 2.6 | |
| CPAAModel=Average across models2026.04 | 95 | 2.5 | |
| CPDAAModel=Average across models2026.04 | 95 | 2.5 | |
| ESCModel=Average across models2026.04 | 94.8 | 6.6 | |
| ASCModel=Average across models2026.04 | 94.7 | 5.3 |