Mathematical Problem Solving on MATH-500 (pass@1)
71.98Pass@1Mismatched-wrong
Evaluation Results
| Method | Links | |
|---|---|---|
| Mismatched-wrongBackbone=Mathstral-7B-v0.1, Decoding strategy=Greedy, Evaluation protocol=fine-tuning2026.05 | 71.98 |
Loading the SOTA2 catalog…