General Perception and Reasoning on MathVerse VO
52ScoreClaude-3.7-Sonnet
Evaluation Results
| Method | Links | |
|---|---|---|
| Claude-3.7-SonnetData=-2025.12 | 52 | |
| Vision-R1-7BData=73K + 137K2025.12 | 47.7 | |
| BiPS-General-7BData=13K+39K2025.12 | 45.3 | |
| DeepEyes-7BData=14K + 33K2025.12 | 44.9 | |
| BiPS-Chart-7BData=13K2025.12 | 44.4 | |
| GRPOData=13K + 39K2025.12 | 42.6 | |
| Qwen2.5-VL-7BData=-2025.12 | 41.1 | |
| GPT-4oData=-2025.12 | 40.6 | |
| R1-OneVision-7BData=67K + 98K2025.12 | 40 | |
| InternVL3-8BData=-2025.12 | 33.9 | |
| Chart-R1-7BData=258K2025.12 | 28.1 |