| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multi-image reasoning | OmniContext | Single Scene Char Score8.96 | 20 | |
| In-context image generation | OmniContext 1.0 (test) | Single Instance Character Fidelity8.9 | 13 | |
| Anything-to-Image | OmniContext Overall | Average Score9.35 | 12 | |
| Anything-to-Image | OmniContext SCENE | Character Fidelity9.56 | 12 | |
| Anything-to-Image | OmniContext MULTIPLE | Character Fidelity Score9.56 | 12 | |
| Subject-Consistent Image Generation | OmniContext | Fidelity (Single, Character)9.24 | 10 | |
| In-context generation | OmniContext SINGLE | Character Fidelity8.9 | 10 | |
| Multi-reference image generation | OmniContext SCENE 1.0 (test) | Character Fidelity Score8.9 | 10 | |
| Multi-reference image generation | OmniContext MULTIPLE 1.0 (test) | Character Score9.07 | 10 | |
| Subject-Driven Image Generation | OmniContext SINGLE 1.0 | Character PF Score8.89 | 10 | |
| Anything-to-Image | OmniContext SINGLE | Character Score9.4 | 9 | |
| In-context generation | OmniContext | Average Performance Score8.8 | 8 | |
| In-context generation | OmniContext SCENE | Character Score8.9 | 8 | |
| In-context generation | OmniContext MULTIPLE | Character Score9.07 | 8 | |
| In-context Image Generation | OmniContext (test) | Prompt Following7.58 | 5 | |
| In-context Video Generation | OmniContext-Video | Single ID Char Score6.71 | 3 |