General Perception and Reasoning on MathVision
58.6ScoreClaude-3.7-Sonnet
Evaluation Results
| Method | Links | |
|---|---|---|
| Claude-3.7-SonnetData=-2025.12 | 58.6 | |
| GPT-4oData=-2025.12 | 31.2 | |
| R1-OneVision-7BData=67K + 98K2025.12 | 29.9 | |
| BiPS-General-7BData=13K+39K2025.12 | 28.6 | |
| GRPOData=13K + 39K2025.12 | 27.3 | |
| BiPS-Chart-7BData=13K2025.12 | 27.2 | |
| DeepEyes-7BData=14K + 33K2025.12 | 26.5 | |
| InternVL3-8BData=-2025.12 | 26.3 | |
| Qwen2.5-VL-7BData=-2025.12 | 25.2 | |
| Chart-R1-7BData=258K2025.12 | 20.6 |