Mathematical Reasoning on MathVerse mini All (test)
56.7CoT-EMathFlow
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MathFlowPerception Model=MathFlow-P-7B, Inference Model=GPT-4V2025.03 | 56.7 | 43.8 | |
| GPT-4V2025.03 | 54.4 | 39.4 | |
| MathFlowPerception Model=MathFlow-P-7B, Inference Model=Qwen2-VL-72B2025.03 | 40.5 | 31.7 | |
| Qwen2-VL-72B2025.03 | 38.9 | 28.5 | |
| Qwen-VL-Max2025.03 | 37.2 | 25.3 | |
| Gemini-Pro2025.03 | 35.3 | 23.5 | |
| InfiMM-Math2025.03 | 34.5 | — | |
| MAVIS-7B2025.03 | 27.5 | — | |
| InternLM-XC22025.03 | 25.9 | 16.5 | |
| SPHINX-MoE2025.03 | 25.8 | 15.6 | |
| Qwen-VL-Plus2025.03 | 21.3 | 11.8 |