| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MLLM-as-a-Judge in-domain v1.0 (test) | LLaVA-Critic-72B | ImageDC Score80.2 | 9 | 3d ago | |
| MMHal pointwise | LLaVA-Critic | Kendall's Tau0.949 | 9 | 3d ago | |
| L-Wilder pointwise | LLaVA-Critic | Kendall's Tau0.994 | 9 | 3d ago | |
| LLaVA-W pointwise | LLaVA-Critic-7B | Kendall's Tau0.949 | 9 | 3d ago | |
| LLaVA-B pointwise | LLaVA-Critic-7B | Kendall's Tau0.846 | 9 | 3d ago | |
| WildVision (pointwise) | LLaVA-Critic | Kendall's Tau0.949 | 9 | 3d ago | |
| MMVet pointwise | LLaVA-Critic | Kendall's Tau0.974 | 9 | 3d ago | |
| ImageDC pointwise | LLaVA-Critic | Kendall's Tau0.949 | 9 | 3d ago |
