| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multimodal Search | MM-BrowseComp (MMBC) | Success Rate30.1 | 15 | |
| Multimodal Search | MM-BrowseComp | Accuracy10.8 | 14 | |
| Multimodal long-horizon complex reasoning | MM-BrowseComp | Score41.1 | 13 | |
| Multimodal Search | MM-BrowseComp (test) | Accuracy16.1 | 12 | |
| Multimodal Search | MM-BrowseComp | Score46.3 | 10 | |
| Vision Agent Capacity | MM-BrowseComp | Score48.8 | 6 | |
| Visual Search | MM-BrowseComp | Pass@146.3 | 4 |