Image Editing on RISEBench (test)
77Instruction ReasoningNano Banana Pro
Evaluation results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Nano Banana ProModel Category=Commercial Models2026.06 | 77 | 85.5 | 94.4 | 43.5 | 63.3 | 48 | 37.6 | 48.3 | |
| GPT-Image-2Model Category=Commercial Models2026.06 | 73.8 | 89.3 | 94.9 | 45.9 | 66.7 | 50 | 34.1 | 49.4 | |
| RS-GenModel Category=Image Agentic Systems2026.06 | 69.9 | 91.1 | 93.6 | 36.4 | 50 | 40 | 29.4 | 39.1 | |
| GPT-Image-1.5Model Category=Commercial Models2026.06 | 69.7 | 92.5 | 94.9 | 57.6 | 62.2 | 62 | 21.2 | 51.4 | |
| GPT-Image-1Model Category=Commercial Models2026.06 | 62.8 | 80.2 | 94.9 | 36.5 | 34.4 | 37 | 10.6 | 30 | |
| Mind-BrushModel Category=Image Agentic Systems2026.06 | 61.5 | 79.4 | 86.5 | — | — | — | — | 24.7 | |
| Nano BananaModel Category=Commercial Models2026.06 | 61.2 | 86 | 91.3 | 29.4 | 48.9 | 37 | 18.8 | 33.9 | |
| Seedream-4.0Model Category=Commercial Models2026.06 | 58.9 | 67.4 | 91.2 | 17.6 | 13.3 | 11 | 7.1 | 12.2 | |
| GPT-Image-1-miniModel Category=Commercial Models2026.06 | 54.1 | 71.5 | 93.7 | 25.9 | 31.1 | 33 | 9.4 | 25.3 | |
| Gemini-2.0-Flash-preModel Category=Open-Source Models2026.06 | 49.9 | 68.4 | 84.9 | 11.8 | 14.4 | 11 | 2.4 | 10 | |
| Qwen-Image-Edit-2511Model Category=Open-Source Models2026.06 | 49.9 | 71 | 91.5 | 21.2 | 18.9 | 31 | 4.7 | 19.4 | |
| Gemini-2.0-Flash-expModel Category=Open-Source Models2026.06 | 48.9 | 68.2 | 82.7 | 9.4 | 16.7 | 23 | 4.7 | 13.9 | |
| BAGELModel Category=Open-Source Models, Reasoning Strategy=CoT2026.06 | 45.9 | 73.8 | 80.1 | 5.9 | 17.8 | 21 | 1.2 | 11.9 | |
| Qwen-Image-Edit-2509Model Category=Open-Source Models2026.06 | 37.2 | 66.4 | 86.9 | 4.7 | 11.1 | 17 | 2.4 | 9.2 | |
| BAGELModel Category=Open-Source Models2026.06 | 36.5 | 53.5 | 73 | 2.4 | 5.6 | 14 | 1.2 | 6.1 | |
| Ovis-U1Model Category=Open-Source Models2026.06 | 33.9 | 52.7 | 72.9 | 1.1 | 3.3 | 4 | 2.4 | 2.8 | |
| HiDream-EditModel Category=Open-Source Models2026.06 | 30.3 | 12.6 | 74.9 | 0 | 0 | 0 | 0 | 0 | |
| FLUX.1-Kontext-DevModel Category=Open-Source Models2026.06 | 26 | 71.6 | 85.2 | 2.3 | 5.5 | 13 | 1.2 | 5.8 | |
| Step1X-EditModel Category=Open-Source Models2026.06 | 25.1 | 41.5 | 73.5 | 0 | 2.2 | 2 | 3.5 | 1.9 | |
| EMU2Model Category=Open-Source Models2026.06 | 22.6 | 38.2 | 78.3 | 1.2 | 1.1 | 0 | 0 | 0.5 | |
| OmniGenModel Category=Open-Source Models2026.06 | 22 | 32.6 | 55.3 | 1.2 | 1.1 | 0 | 1.2 | 0.8 | |
| FLUX.1-CannyModel Category=Open-Source Models2026.06 | 20.2 | 13.1 | 77.5 | 0 | 0 | 0 | 0 | 0 |