| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Visual Question Answering | SimpleVQA | Accuracy0.743 | 164 | |
| General visual question answering | SimpleVQA | Pass@176.2 | 33 | |
| Multimodal Search | SimpleVQA | Accuracy64.1 | 15 | |
| Visual Question Answering | SimpleVQA-EN | Accuracy50.6 | 14 | |
| Expert Reasoning | SimpleVQA | Accuracy39.78 | 12 | |
| Factuality | SimpleVQA | Factuality Score43.51 | 8 | |
| Visual instruction tuning | SimpleVQA | Score49.5 | 6 | |
| General VQA | SimpleVQA | Accuracy74.06 | 5 |