Step-wise Verification on MathVerse VO
62.8Macro F1Gemini-2.0-Flash
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-2.0-FlashModel Type=Proprietary2025.11 | 62.8 | |
| TIM-PRMModel Type=Open-source, Number of Parameters=8B2025.11 | 61.9 | |
| TIM-PRMModel Type=Open-source, Number of Parameters=2B2025.11 | 61.7 | |
| Qwen3-VLModel Type=Open-source, Number of Parameters=8B2025.11 | 59.9 | |
| GPT-4oModel Type=Proprietary2025.11 | 59.7 | |
| Qwen2.5-VLModel Type=Open-source, Number of Parameters=72B2025.11 | 59.7 | |
| MiniCPM-V2.6Model Type=Open-source, Number of Parameters=8B2025.11 | 58.9 | |
| GPT-4o-MiniModel Type=Proprietary2025.11 | 57.1 | |
| MM-PRMModel Type=Open-source, Number of Parameters=8B2025.11 | 54.9 | |
| InternVL2.5Model Type=Open-source, Number of Parameters=78B2025.11 | 53.7 | |
| LLaVA-OVModel Type=Open-source, Number of Parameters=72B2025.11 | 53 | |
| VisualPRMModel Type=Open-source, Number of Parameters=8B2025.11 | 53 | |
| InternVL2.5Model Type=Open-source, Number of Parameters=38B2025.11 | 50.9 | |
| Qwen3-VLModel Type=Open-source, Number of Parameters=2B2025.11 | 49.6 | |
| InternVL2.5Model Type=Open-source, Number of Parameters=26B2025.11 | 49.2 | |
| Qwen2.5-VLModel Type=Open-source, Number of Parameters=7B2025.11 | 47.8 | |
| InternVL2.5Model Type=Open-source, Number of Parameters=8B2025.11 | 47.8 | |
| LLaVA-OVModel Type=Open-source, Number of Parameters=7B2025.11 | 42.2 |