| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| LLaVA-Bench In-the-Wild | GPT-4V | Score93.1 | 23 | 3d ago | |
| ViSiT-Bench Sept. 27th, 2023 (Leaderboard) | ELO1,382 | 15 | 3d ago | ||
| MIA-Bench | Score8.86 | 12 | 3d ago | ||
| LLaVA Wilder | VLSI-7B | Score92 | 9 | 3d ago | |
| TouchStone | Qwen-VL-Chat | English Metric645.2 | 7 | 3d ago | |
| LLaVA-Bench In-the-Wild 1.0 (test) | LLaVA | Conversation58.8 | 4 | 3d ago |