| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Text-to-3D Generation | Text-to-3D evaluation prompts | CLIP Score30.33 | 7 | |
| 3D Generation | Text-to-3D Prompts (test) | Quality7.81 | 6 | |
| Text-to-3D Generation | 28 text-to-3D prompts | Avg User Preference Rank4.76 | 6 | |
| Text-to-3D Generation | Text-to-3D prompts | CLIP Similarity (ViT-L/14)27.39 | 4 |