Image Generation on GenEvolve-Bench Overall
79.7FaithfulnessGenEvolve (strong generator)
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| GenEvolve (strong generator)Generator=Nano Banana Pro, Method Category=agent2026.05 | 79.7 | 38.32 | 62.18 | 57.39 | |
| Nano Banana ProGenerator=Nano Banana Pro, Method Category=raw2026.05 | 77.61 | 28.37 | 61.78 | 52.98 | |
| Gen-Searcher 8BGenerator=Nano Banana Pro, Method Category=agent2026.05 | 74.65 | 33.78 | 61.98 | 54.81 | |
| GenEvolve (open generator)Generator=Qwen-Image-Edit-2511, Method Category=agent2026.05 | 53.03 | 13.38 | 49.07 | 36.63 | |
| Gen-Searcher 8BGenerator=Qwen-Image-Edit-2511, Method Category=agent2026.05 | 52.84 | 10.5 | 47.68 | 34.93 | |
| Qwen-ImageGenerator=Qwen-Image, Method Category=raw2026.05 | 37.29 | 6.23 | 42.26 | 29.87 | |
| FLUX.2 Klein 9BGenerator=FLUX.2, Method Category=raw2026.05 | 36.62 | 2.1 | 41.92 | 27.87 | |
| Z-ImageGenerator=Z-Image, Method Category=raw2026.05 | 33.33 | 2.78 | 43.52 | 27.28 | |
| Z-Image-TurboGenerator=Z-Image, Method Category=raw2026.05 | 28.37 | 3.96 | 43.69 | 28.08 | |
| FLUX.2 Klein 4BGenerator=FLUX.2, Method Category=raw2026.05 | 25.25 | 0.59 | 38.47 | 23.8 | |
| FLUX.1-devGenerator=FLUX.1, Method Category=raw2026.05 | 15.74 | 0.59 | 41.5 | 23.96 | |
| SD-3.5-LargeGenerator=SD-3.5, Method Category=raw2026.05 | 14.56 | 1.35 | 38.72 | 22.35 | |
| BAGELGenerator=BAGEL, Method Category=raw2026.05 | 12.12 | 0.59 | 37.21 | 20.41 | |
| Lumina-Image 2.0Generator=Lumina-Image 2.0, Method Category=raw2026.05 | 10.44 | 0 | 33.08 | 16.97 |