Benchmark
MathVision
math
vision
multimodal
multimodal
MATH-Vision is a dataset designed to measure multimodal mathematical reasoning capabilities. It focuses on evaluating how well models can solve mathematical problems that require both visual understanding and mathematical reasoning, bridging the gap between visual and mathematical domains.
语言EN
满分1
参评模型5
模型排名
| 名次 | 模型 | 机构 | 分数 | 来源 |
|---|---|---|---|---|
| 1 | Qwen2.5 VL 32B Instruct | Alibaba Cloud / Qwen Team | 38.4 | 来源 ↗ |
| 2 | Qwen2.5 VL 72B Instruct | Alibaba Cloud / Qwen Team | 38.1 | 来源 ↗ |
| 3 | QvQ-72B-Preview | Alibaba Cloud / Qwen Team | 35.9 | 来源 ↗ |
| 4 | Qwen2.5 VL 7B Instruct | Alibaba Cloud / Qwen Team | 25.1 | 来源 ↗ |
| 5 | Qwen2.5-Omni-7B | Alibaba Cloud / Qwen Team | 25.0 | 来源 ↗ |