| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Human Preference Agreement | MM-RewardBench2 T2I | Accuracy78.9 | 13 | |
| Text-to-image preference evaluation | MM-RewardBench T2I 2 | Accuracy78.9 | 11 | |
| Human Preference Agreement | MM-RewardBench2 Edit | Accuracy79.2 | 7 | |
| Image editing preference evaluation | MM-RewardBench2 Edit | Accuracy79.2 | 7 |