Mathematical Reasoning on MathVerse Text Only (testmini)
62.1CoT-EMathFlow
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MathFlowPerception Model=MathFlow-P-7B, Inference Model=GPT-4V2025.03 | 62.1 | 48.5 | |
| GPT-4V2025.03 | 60.3 | 48.7 | |
| MathFlowPerception Model=MathFlow-P-7B, Inference Model=Qwen2-VL-72B2025.03 | 55.2 | 45.5 | |
| Qwen2-VL-72B2025.03 | 52.1 | 39.6 | |
| Qwen-VL-Max2025.03 | 47.9 | 28.9 | |
| Gemini-Pro2025.03 | 44.5 | 27.3 | |
| InternLM-XC22025.03 | 42.5 | 16.5 | |
| MAVIS-7B2025.03 | 42.5 | — | |
| SPHINX-MoE2025.03 | 40.7 | 18.3 | |
| Qwen-VL-Plus2025.03 | 25.2 | 14.5 |