Math Reasoning on PRM800K
0.613AUC-ROCSupervised
Evaluation Results
| Method | Links | |
|---|---|---|
| Supervised2024.04 | 0.613 | |
| FRACTAL2024.04 | 0.597 | |
| BagLoss2024.04 | 0.569 | |
| Resp-level2024.04 | 0.528 | |
| cos-sim2024.04 | 0.42 |
| Method | Links | |
|---|---|---|
| Supervised2024.04 | 0.613 | |
| FRACTAL2024.04 | 0.597 | |
| BagLoss2024.04 | 0.569 | |
| Resp-level2024.04 | 0.528 | |
| cos-sim2024.04 | 0.42 |