Step-wise Verification on DynaMath
66.7Macro F1Gemini-2.0-Flash
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-2.0-FlashModel Type=Proprietary2025.11 | 66.7 | |
| TIM-PRMModel Type=Open-source, Number of Parameters=8B2025.11 | 65.9 | |
| TIM-PRMModel Type=Open-source, Number of Parameters=2B2025.11 | 64.3 | |
| Qwen2.5-VLModel Type=Open-source, Number of Parameters=72B2025.11 | 62.9 | |
| Qwen3-VLModel Type=Open-source, Number of Parameters=8B2025.11 | 61.4 | |
| GPT-4oModel Type=Proprietary2025.11 | 59 | |
| MM-PRMModel Type=Open-source, Number of Parameters=8B2025.11 | 58.1 | |
| VisualPRMModel Type=Open-source, Number of Parameters=8B2025.11 | 57.5 | |
| LLaVA-OVModel Type=Open-source, Number of Parameters=72B2025.11 | 57 | |
| GPT-4o-MiniModel Type=Proprietary2025.11 | 56.7 | |
| InternVL2.5Model Type=Open-source, Number of Parameters=38B2025.11 | 51.8 | |
| Qwen2.5-VLModel Type=Open-source, Number of Parameters=7B2025.11 | 51.3 | |
| InternVL2.5Model Type=Open-source, Number of Parameters=78B2025.11 | 50.8 | |
| InternVL2.5Model Type=Open-source, Number of Parameters=26B2025.11 | 50.4 | |
| InternVL2.5Model Type=Open-source, Number of Parameters=8B2025.11 | 50.3 | |
| Qwen3-VLModel Type=Open-source, Number of Parameters=2B2025.11 | 48.7 | |
| MiniCPM-V2.6Model Type=Open-source, Number of Parameters=8B2025.11 | 46.7 | |
| LLaVA-OVModel Type=Open-source, Number of Parameters=7B2025.11 | 44.7 |