Text-to-Image Prompt Following on DenseAlignBench
61.5Win RateZ-Image + PromptEcho
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| Z-Image + PromptEchoBase Model=Z-Image, Evaluator=Gemini-3-flash-preview, Resolution=1024×1024, CFG=4.0, Inference steps=502026.04 | 61.5 | 34.7 | 3.8 | 26.8 | |
| QwenImage-2512 + PromptEchoBase Model=QwenImage-2512, Evaluator=Gemini-3-flash-preview, Resolution=1024×1024, CFG=4.0, Inference steps=502026.04 | 53.3 | 37 | 9.7 | 16.2 |