| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multimodal Multilingual Reasoning | MMMB | English Accuracy86.8 | 39 | |
| Visual Question Answering | MMMB (test) | Accuracy84.75 | 32 | |
| Visual Understanding | MMMB | Accuracy (Clean)81.41 | 7 | |
| Multilingual Multimodal Understanding | MMMB | Score (AR)76.9 | 5 |