Image Generation on GenEval 129
88Overall Performance ScoreLumina-DiMOO
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| Lumina-DiMOOModel Category=Unified2026.03 | 88 | 100 | 94 | 85 | 89 | 85 | 76 | |
| Qwen-ImageModel Category=Generation-Experts2026.03 | 87 | 99 | 92 | 89 | 88 | 76 | 77 | |
| Dynin-OmniModel Category=Unified, Native speech input/output capability (†)=true2026.03 | 87 | 100 | 93 | 81 | 91 | 87 | 73 | |
| NExT-OMNIModel Category=Unified, Video generation support (*)=true, Native speech input/output capability (†)=true2026.03 | 85 | 99 | 92 | 79 | 85 | 78 | 74 | |
| GPT-Image 1 [High]Model Category=Generation-Experts2026.03 | 84 | 99 | 92 | 85 | 92 | 75 | 61 | |
| Seedream 3.0Model Category=Generation-Experts2026.03 | 84 | 99 | 96 | 91 | 93 | 47 | 80 | |
| HiDream-I1-FullModel Category=Generation-Experts2026.03 | 83 | 100 | 98 | 79 | 91 | 60 | 72 | |
| BAGLEModel Category=Unified2026.03 | 82 | 99 | 94 | 81 | 88 | 64 | 63 | |
| Janus-ProModel Category=Unified2026.03 | 80 | 99 | 89 | 59 | 90 | 79 | 66 | |
| FudokiModel Category=Unified2026.03 | 77 | 96 | 85 | 56 | 88 | 68 | 67 | |
| Show-o2Model Category=Unified, Video generation support (*)=true2026.03 | 76 | 100 | 87 | 58 | 92 | 52 | 62 | |
| FLUX.1 [Dev]Model Category=Generation-Experts2026.03 | 66 | 98 | 81 | 74 | 79 | 22 | 45 | |
| Emu3Model Category=Unified2026.03 | 66 | 99 | 81 | 42 | 80 | 49 | 45 | |
| HyperCLOVAX-8B-OmniModel Category=Unified, Native speech input/output capability (†)=true2026.03 | 64 | — | — | — | — | — | — | |
| MMaDAModel Category=Unified2026.03 | 63 | 99 | 76 | 61 | 84 | 20 | 37 |