Edit-Compass: leaderboard
Edit-Compass (2026) tests instruction-based image editing on 2,388 instances with English instructions in six categories (general editing, dynamic manipulation, world knowledge, visual reasoning, multi-image and complex tasks), judged by Gemini 3.1 Pro with rubric prompts on a 1-5 scale. The overall combines instruction awareness, visual consistency and visual quality per category; higher is better.
Metric: Overall score (1-5) of image editing under English instructions, Gemini-3.1-Pro judge with rubric prompts rates instruction awareness, visual consistency and visual quality on a 1-5 scale; the per-category overall is a weighted geometric mean, set to the lowest dimension when that is at most 1; 2,388 instances in six categories (models without multi-image input print no multi-image scores); higher is better. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 29 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Nano Banana Pro | 3.99 | |
| 2 | Nano Banana 2 | 3.74 | |
| 3 | Wan2.7-Image | 3.23 | |
| 4 | Seedream 4.5 | 3.22 | |
| 5 | Qwen-Image-Edit-2511 | 2.69 | |
| 6 | JoyAI-Image-Edit | 2.68 | |
| 7 | EMU3.5 | 2.66 | |
| 8 | LongCat-Image-Edit | 2.65 | |
| 9 | FLUX.2-dev | 2.61 | |
| 10 | Step1X-Edit-v1p2 | 2.58 | |
| 11 | UniWorld-V2 | 2.53 | |
| 12 | Skywork UniPic 3.0 | 2.35 | |
| 13 | Bagel | 2.1 | |
| 14 | Bagel-Think | 2.08 | |
| 15 | FLUX.1-Kontext-dev | 1.93 |
Interactive version: theaggregate.ai/benchmark?slug=edit-compass · How It Works · Data refreshed daily, snapshot 2026-11-21.