WeEdit (Bilingual) - Add: leaderboard
Metric: Mean instruction-adherence score (0-10 judge scale) on the add operation of the WeEdit Bilingual Benchmark (2,000 text-centric image-editing cases), rated by a Gemini-3-Pro judge that writes a chain-of-thought rationale before scoring whether the edited image fulfils every requirement of the instruction; higher is better. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 15 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Nano Banana Pro | 9.38 | |
| 2 | GPT-Image-1.5 | 8.02 | |
| 3 | Seedream 4.5 | 6.86 | |
| 4 | HunyuanImage-3.0-Instruct | 6.04 | |
| 5 | Gemini 2.5 Flash Image | 5.88 | |
| 6 | FireRed-Image-Edit | 5.44 | |
| 7 | FLUX.2-dev | 5.4 | |
| 8 | LongCat-Image-Edit | 5.23 | |
| 9 | UniWorld-V2 | 5.15 | |
| 10 | Qwen-Image-Edit-2509 | 4.96 |
Interactive version: theaggregate.ai/benchmark?slug=weedit-bilingual-add · How It Works · Data refreshed daily, snapshot 2026-10-11.