Mathematical Reasoning on MathVerse Text Dominant (testmini)
65.2CoT-EMathFlow
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MathFlowPerception Model=MathFlow-P-7B, Inference Model=GPT-4V2025.03 | 65.2 | 51.1 | |
| GPT-4V2025.03 | 63.1 | 54.7 | |
| MathFlowPerception Model=MathFlow-P-7B, Inference Model=Qwen2-VL-72B2025.03 | 52.3 | 39.3 | |
| Qwen2-VL-72B2025.03 | 49.2 | 35.4 | |
| InfiMM-Math2025.03 | 46.7 | — | |
| Qwen-VL-Max2025.03 | 42.8 | 30.7 | |
| MAVIS-7B2025.03 | 41.4 | — | |
| Gemini-Pro2025.03 | 39.8 | 26.3 | |
| InternLM-XC22025.03 | 36.9 | 22.3 | |
| SPHINX-MoE2025.03 | 33.3 | 22.2 | |
| Qwen-VL-Plus2025.03 | 26 | 15.7 |