| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Fine-grained Visual Reasoning | MME-RW-Lite ID | Overall Score57 | 20 | |
| Real-world Multimodal Evaluation | MME-RW (test) | Overall Score62.9 | 15 | |
| Multimodal Understanding | MME-RW-en (test) | Overall Score71.4 | 15 | |
| Visual Reasoning | MME-RW Chinese | Accuracy77.7 | 14 |