Mathematical Reasoning on MathVerse Vision Dominant (testmini)
19.1CoT-EQwen-VL-Plus
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Qwen-VL-Plus2025.03 | 19.1 | 13 | |
| SPHINX-MoE2025.03 | 19.6 | 12.6 | |
| InternLM-XC22025.03 | 24.4 | 16.4 | |
| MAVIS-7B2025.03 | 24.9 | — | |
| InfiMM-Math2025.03 | 32.4 | — | |
| Qwen2-VL-72B2025.03 | 35.1 | 28.5 | |
| Qwen-VL-Max2025.03 | 35.9 | 24.1 | |
| Gemini-Pro2025.03 | 36.8 | 22.3 | |
| MathFlowPerception Model=MathFlow-P-7B, Inference Model=Qwen2-VL-72B2025.03 | 37.2 | 32.4 | |
| GPT-4V2025.03 | 50.8 | 34.4 | |
| MathFlowPerception Model=MathFlow-P-7B, Inference Model=GPT-4V2025.03 | 52.1 | 37.4 |