GRADE (Image Editing) - Biology: leaderboard
Metric: Accuracy (%): share of samples that get the maximum score on discipline reasoning, visual consistency and logical readability at once, on the 54 biology samples on GRADE's 520 discipline-informed image editing samples (input image, editing instruction and ground-truth image across 10 academic disciplines), a Gemini-3-Flash judge scoring reasoning against expert-verified weighted questions (written by GPT-5) and visual consistency and logical readability on 0/1/2 scales; higher is better. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 20 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Nano Banana Pro | 55.6 | |
| 2 | Seedream 5.0 Lite | 45.3 | |
| 3 | Nano Banana 2 | 38.9 | |
| 4 | FLUX.2-max | 29.6 | |
| 5 | GPT-Image-1.5 | 22.2 | |
| 6 | Nano Banana | 13 | |
| 7 | Seedream 4.5 | 11.3 | |
| 8 | GPT-Image-1 | 11.1 | |
| 9 | Step1X-Edit (Thinking + Reflection) | 7.4 | |
| 10 | FLUX 2 Pro | 5.6 |
Interactive version: theaggregate.ai/benchmark?slug=grade-image-editing-biology · How It Works · Data refreshed daily, snapshot 2026-10-11.