First Incorrect Step Identification on WeMath
24.9FISI F1 Score
TIM-PRM-8B
Updated 2d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2025.11 | 24.9 | |
2025.11 | 23.9 | |
2025.11 | 18.8 | |
2025.11 | 12.2 | |
2025.11 | 7.8 | |
2025.11 | 6.4 |
TIM-PRM-8B
| Method | Links | |
|---|---|---|
2025.11 | 24.9 | |
2025.11 | 23.9 | |
2025.11 | 18.8 | |
2025.11 | 12.2 | |
2025.11 | 7.8 | |
2025.11 | 6.4 |