| Benchmark | Model | Rank | Results |
|---|---|---|---|
| image-editing-on-gedit-bench-en | ARR-RPO (Gemini 3.1 Pro-ARR) | #7 | Overall: 7.85 |
| text-to-image-generation-on-dpg-bench | FLUX.1-dev + ARR-RPO (Gemini 3.1 Pro judge) | #52 | DPG-Bench Score: 85.76 |
| text-to-image-generation-on-geneval | FLUX.1-dev + ARR-RPO (Gemini 3.1 Pro judge) | #103 | Overall: 0.8 |