Mathematical Reasoning on MathVision (Detailed Sub-scores)
32.01Overall ScoreMathFlow
Evaluation Results
| Method | Links | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| MathFlowBackbone=GPT-4V, Setting=Zero-shot, Prompting=Chain-of-Thought2025.03 | 32.01 | 43.9 | 38.7 | 48.5 | 28.2 | 29 | 25.4 | 17.7 | 30.6 | 32.1 | 32.9 | 30.7 | 35.1 | 31.5 | 40 | 20.3 | 26 | |
| GPT-4TurboSetting=Zero-shot, Prompting=Chain-of-Thought2025.03 | 30.26 | 37.7 | 33.3 | 46.4 | 25 | 28.6 | 25.3 | 15.4 | 27.8 | 31.9 | 30.6 | 29 | 31.9 | 28.7 | 37.9 | 17.4 | 23.2 | |
| MathFlowBackbone=Qwen2-VL-72B, Setting=Zero-shot, Prompting=Chain-of-Thought2025.03 | 28.14 | 38.2 | 36.5 | 47.5 | 27.1 | 23.8 | 20.6 | 22.2 | 21.5 | 27.6 | 19.5 | 24 | 28.3 | 27.3 | 33 | 35 | 18.1 | |
| Qwen2-VL-72BSetting=Zero-shot, Prompting=Chain-of-Thought2025.03 | 25.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Gemini ProSetting=Zero-shot, Prompting=Chain-of-Thought2025.03 | 17.66 | 15.1 | 10.7 | 20.7 | 20.1 | 11.9 | 7.5 | 20.2 | 21.1 | 16.8 | 19.1 | 19 | 20 | 14.3 | 13.8 | 17.4 | 20.8 | |
| Qwen-VL-MaxSetting=Zero-shot, Prompting=Chain-of-Thought2025.03 | 15.59 | 10.7 | 19.1 | 20 | 16.9 | 12.5 | 17.9 | 16.4 | 12.2 | 21 | 13.3 | 14.2 | 19.8 | 11.5 | 20.7 | 13 | 17.3 | |
| InternLM-VLSetting=Zero-shot, Prompting=Chain-of-Thought2025.03 | 14.54 | 9.3 | 15.5 | 12.1 | 15.3 | 11.3 | 10.5 | 14.4 | 22.2 | 19.3 | 19.7 | 15.6 | 15 | 11.9 | 15.5 | 26.1 | 15.5 | |
| SPHINX-MoESetting=Zero-shot, Prompting=Chain-of-Thought2025.03 | 14.18 | 7.8 | 17.9 | 14.3 | 15.6 | 9.5 | 11.9 | 12.5 | 15.6 | 12.6 | 16.2 | 15.6 | 17.8 | 13.5 | 12.1 | 8.7 | 16.1 | |
| ShareGPT4V-13BSetting=Zero-shot, Prompting=Chain-of-Thought2025.03 | 11.88 | 7.5 | 15.5 | 16.4 | 10.7 | 8.9 | 9 | 11.5 | 8.9 | 7.6 | 11.6 | 13 | 17.4 | 10.3 | 8.6 | 8.7 | 12.5 | |
| Qwen-VL-PlusSetting=Zero-shot, Prompting=Chain-of-Thought2025.03 | 10.72 | 11.3 | 17.9 | 14.3 | 12.7 | 4.8 | 10.5 | 15.4 | 8.9 | 14.3 | 11.6 | 6.4 | 10 | 14.3 | 6.9 | 8.7 | 11.31 |