Multimodal Generation on GenEval
90ScoreOneCAT
Evaluation Results
| Method | Links | |
|---|---|---|
| OneCAT2026.03 | 90 | |
| Mogao2026.03 | 89 | |
| Ovis-U12026.03 | 89 | |
| Lumina2026.03 | 88 | |
| NEO-unify2026.03 | 85 | |
| InternVL-U2026.03 | 85 | |
| BLIP3-o2026.03 | 84 | |
| LongCat-Next2026.03 | 84 | |
| X-Omni2026.03 | 83 | |
| BAGEL2026.03 | 82 | |
| Janus-Pro2026.03 | 80 | |
| OmniGen22026.03 | 80 | |
| UniWorld-V12026.03 | 80 | |
| Show-o22026.03 | 76 | |
| Janus-ProInterleaved text-image output=false, Params=7B, #Train images=72M, Image resolution=3842026.03 | 0.8 | |
| TokenFlow-XLInterleaved text-image output=false, Params=13B, #Train images=60M, Image resolution=3842026.03 | 0.55 | |
| SEED-XInterleaved text-image output=false, Params=17B, #Train images=158M, Image resolution=N/A2026.03 | 0.49 | |
| UnifiedGRPOInterleaved text-image output=true, Params=7B, #Train images=16M, Image resolution=2562026.03 | 0.46 | |
| VILA-UInterleaved text-image output=false, Params=7B, #Train images=15M, Image resolution=3842026.03 | 0.42 | |
| ChameleonInterleaved text-image output=true, Params=7B, #Train images=1.4B, Image resolution=5122026.03 | 0.39 | |
| ARMORInterleaved text-image output=true, Params=8B, #Train images=5M, Image resolution=2562026.03 | 0.37 |