First Incorrect Step Identification on WeMath
24.9FISI F1 ScoreTIM-PRM-8B
Evaluation Results
| Method | Links | |
|---|---|---|
| TIM-PRM-8BModel=TIM-PRM-8B2025.11 | 24.9 | |
| TIM-PRM-2BModel=TIM-PRM-2B2025.11 | 23.9 | |
| Qwen3-VL-8BModel=Qwen3-VL-8B2025.11 | 18.8 | |
| MM-PRM-8BModel=MM-PRM-8B2025.11 | 12.2 | |
| Qwen3-VL-2BModel=Qwen3-VL-2B2025.11 | 7.8 | |
| VisualPRM-8BModel=VisualPRM-8B2025.11 | 6.4 |