Leaderboard
Human-preference Elo for instruction-based image editing models, ranked head-to-head in the Artificial Analysis Arena.
| # | Model | Elo |
|---|---|---|
| 1 | FLUX 3 Image Black Forest Labs | 1,122 |
| 2 | Qwen-Image-2.1 Qwen · Alibaba | 1,081 |
| 3 | FLUX 3 Image Klein Black Forest Labs | 1,072 |
| 4 | HunyuanImage 3.0 Instruct Tencent | 1,063 |
| 5 | HunyuanImage 3.0 Tencent | 1,029 |
| 6 | FLUX.2 [dev] Turbo Fal | 1,019 |
| 7 | FLUX.2 [klein] 9B Black Forest Labs | 1,015 |
| 8 | FLUX.2 [dev] Black Forest Labs | 1,000 |
| 9 | Qwen Image 2.0 Qwen · Alibaba | 966 |
| 10 | HiDream-O1-Image HiDream | 954 |
| 11 | FLUX.2 [klein] 4B Black Forest Labs | 938 |
| 12 | Qwen Image Edit Qwen · Alibaba | 889 |
| 13 | FLUX.1 Kontext [dev] Black Forest Labs | 883 |
| 14 | HiDream-O1-Image-Dev HiDream | 880 |
| 15 | GLM-Image Zhipu AI | 824 |
| 16 | Bagel ByteDance | 792 |
Leaderboard data is cached from Artificial Analysis Arena and refreshed every 12 hours. Scores shown are for reference; see the source for full methodology.