| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| LLaVA-Bench Wild | InternLM-XComposer2 | Score81.8 | 35 | 3d ago | |
| FronTalk Multi-Turn 1.0 (test) | PR Score75 | 32 | 3d ago | ||
| LLaVA-W | Score102 | 28 | 3d ago | ||
| FronTalk Single-Turn 1.0 (test) | PR77.5 | 20 | 3d ago | ||
| LLaVA-Bench | LLaVA-RLHF | Conversation Score93.9 | 8 | 3d ago | |
| Visual Instruction Total (test) | PromptEnhancer | Avg. Response Length (Words)153.04 | 6 | 3d ago | |
| LLaVA-Bench 100 images (test) | Nullu | Accuracy6.53 | 6 | 3d ago | |
| Visual Instruction Out-Of-Distribution - Hard (test) | BeautifulPrompt | Win Ratio (Human)88 | 5 | 3d ago | |
| Visual Instruction Out-Of-Distribution - Simple (test) | BeautifulPrompt | Human Win Ratio93 | 5 | 3d ago | |
| Visual Instruction Out-Of-Distribution (test) | BeautifulPrompt | Human Win Ratio90 | 5 | 3d ago | |
| Visual Instruction In-Distribution - Hard (test) | BeautifulPrompt | Human Win Ratio89 | 5 | 3d ago | |
| Visual Instruction In-Distribution - Simple (test) | BeautifulPrompt | Human Win Ratio89 | 5 | 3d ago | |
| Visual Instruction In-Distribution (test) | BeautifulPrompt | Human Win Ratio89 | 5 | 3d ago |
