TinyGrafixBench - Scatter Plot: leaderboard
Metric: mIoU (%). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-Image-2 | 6.8 |
| 2 | FLUX.1-Kontext-dev | 4.3 |
| 3 | Nano-Banana-2 | 4.2 |
| 4 | FLUX.2-dev | 4.2 |
| 5 | Nano Banana | 3.7 |
| 6 | BAGEL-7B-MoT | 2.1 |
| 7 | FLUX.2-klein-9B | 2.1 |
| 8 | Qwen-Image-Edit-2511 | 1.3 |
| 9 | LongCat-Image-Edit | 1 |
| 10 | InstructPix2Pix | 0.3 |
Interactive version: theaggregate.ai/benchmark?slug=tinygrafixbench-scatter-plot · How It Works · Data refreshed daily, snapshot 2026-09-26.