Image editing arena
From Wikiprompt, the free prompt encyclopedia
Community Elo leaderboard, aggregated daily from LMArena head-to-head battles. Overall arena first, then per-category breakdowns.
Last updated: 2026-08-24 · 53 models
| Rank | Model | Organization | Elo score |
|---|---|---|---|
| 1 | gpt-image-2 (medium) | openai | 1,463 |
| 2 | grok-imagine-image-2.0 (low) | xai | 1,439 |
| 3 | mai-image-2.6-preview | microsoft-ai | 1,420 |
| 4 | muse-image | meta | 1,406 |
| 5 | mai-image-2.5 | microsoft-ai | 1,401 |
| 6 | seedream-5.0-pro | bytedance | 1,394 |
| 7 | grok-imagine-image-quality (20260519) | xai | 1,390 |
| 8 | gemini-3-pro-image-2k (nano-banana-pro) | 1,390 | |
| 9 | chatgpt-image-latest-high-fidelity (20251216) | openai | 1,389 |
| 10 | gemini-3.1-flash-image (nano-banana-2) [web-search] | 1,386 | |
| 11 | gemini-3-pro-image-preview (nano-banana-pro) | 1,385 | |
| 12 | reve-2.1 | reve | 1,375 |
| 13 | gpt-image-1.5-high-fidelity | openai | 1,370 |
| 14 | reve-2.0 | reve | 1,358 |
| 15 | uni-1.1-max | luma-ai | 1,334 |
| 16 | grok-imagine-image | xai | 1,330 |
| 17 | gemini-3.1-flash-lite-image (nano-banana-2-lite) | 1,314 | |
| 18 | uni-1.1 | luma-ai | 1,312 |
| 19 | qwen-image-2.0-pro-2026-06-22 | alibaba | 1,304 |
| 20 | hunyuan-image-3.0-instruct | tencent | 1,303 |
| 21 | wan2.7-image-pro | alibaba | 1,302 |
| 22 | seedream-4.5 | bytedance | 1,302 |
| 23 | wan2.7-image | alibaba | 1,301 |
| 24 | gemini-2.5-flash-image-preview (nano-banana) | 1,293 | |
| 25 | seedream-5.0-lite | bytedance | 1,293 |
| 26 | seedream-4-2k | bytedance | 1,271 |
| 27 | flux-2-max | bfl | 1,262 |
| 28 | reve-v1.1 | reve | 1,261 |
| 29 | kling-image-o1 | kling | 1,251 |
| 30 | flux-2-pro | bfl | 1,244 |
| 31 | qwen-image-edit | alibaba | 1,241 |
| 32 | qwen-image-edit-2511 | alibaba | 1,235 |
| 33 | reve-v1 | reve | 1,234 |
| 34 | wan2.6-image | alibaba | 1,230 |
| 35 | flux-2-flex | bfl | 1,225 |
| 36 | flux-2-dev | bfl | 1,225 |
| 37 | flux-2-klein-9b | bfl | 1,224 |
| 38 | seedream-4-high-res-fal | bytedance | 1,217 |
| 39 | p-image-edit | 1,211 | |
| 40 | seedream-4-fal | bytedance | 1,210 |
| 41 | reve-v1.1-fast | reve | 1,207 |
| 42 | reve-edit-fast | reve | 1,198 |
| 43 | flux-2-klein-4b | bfl | 1,188 |
| 44 | wan2.5-i2i-preview | alibaba | 1,181 |
| 45 | flux-1-kontext-max | bfl | 1,181 |
| 46 | flux-1-kontext-pro | bfl | 1,176 |
| 47 | flux-1-kontext-dev | bfl | 1,149 |
| 48 | gpt-image-1 | openai | 1,139 |
| 49 | seededit-3.0 | bytedance | 1,139 |
| 50 | gpt-image-1-mini | openai | 1,124 |
| 51 | gemini-2.0-flash-preview-image-generation | 1,081 | |
| 52 | bagel | bytedance | 1,026 |
| 53 | step1x-edit | stepfun | 998 |
By category
Multi image edit
| Rank | Model | Organization | Elo score |
|---|---|---|---|
| 1 | gpt-image-2 (medium) | openai | 1,454 |
| 2 | seedream-5.0-pro | bytedance | 1,414 |
| 3 | muse-image | meta | 1,401 |
| 4 | gemini-3-pro-image-preview (nano-banana-pro) | 1,368 | |
| 5 | gemini-3.1-flash-image (nano-banana-2) [web-search] | 1,365 | |
| 6 | gemini-3-pro-image-2k (nano-banana-pro) | 1,364 | |
| 7 | chatgpt-image-latest-high-fidelity (20251216) | openai | 1,353 |
| 8 | reve-2.0 | reve | 1,344 |
| 9 | gpt-image-1.5-high-fidelity | openai | 1,342 |
| 10 | uni-1.1-max | luma-ai | 1,308 |
| 11 | seedream-4.5 | bytedance | 1,291 |
| 12 | wan2.7-image-pro | alibaba | 1,289 |
| 13 | uni-1.1 | luma-ai | 1,287 |
| 14 | gemini-3.1-flash-lite-image (nano-banana-2-lite) | 1,286 | |
| 15 | wan2.7-image | alibaba | 1,280 |
See also
Sources and methodology
Rankings above are aggregated from open community evaluations. Elo ratings, confidence intervals and vote counts come from LMArena (crowdsourced head-to-head model battles, published as an open dataset). Model pricing and context metadata come from the public OpenRouter API. Wikiprompt snapshots these sources daily and preserves the history; we run no proprietary evaluations of our own.