| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Text-to-Image | PickScore 15 (test) | PickScore23.566 | 17 | |
| Text-to-Video Generation | PickScore | PickScore21.18 | 9 | |
| Text-to-image alignment | PickScore | Reward23.21 | 6 | |
| Human Preference Alignment | PickScore | PickScore (Task)23.55 | 5 | |
| Human Preference Alignment | PickScore | PickScore86.851 | 4 | |
| Text-to-Image Generation | PickScore | PickScore52.1 | 2 |