Qwen-Image-Bench (English) - Quality: leaderboard

Qwen-Image-Bench (2026) scores text-to-image models on 1,000 creator-designed prompts in five pillars: quality, aesthetics, alignment, real-world fidelity and creative generation. This board is the visual quality pillar score from the judge model on the English prompts, 0 to 100; higher is better.

Metric: Visual quality pillar Q-Judger score (0-100), the unified judge model fine-tuned from Qwen3.6-27B on expert annotations, aggregated bottom-up from 56 third-level facets, over the 1,000 creator-designed English prompts; higher is better. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 18 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT Image 259.09
2GPT Image 1.555.78
3Nano Banana Pro55.3
4Qwen Image 2.0 Pro55.16
5Nano Banana 254.86
6Seedream 4.054.4
7Seedream 4.554.05
8Seedream 5.054.01
9FLUX 2 Max53.99
10FLUX 2 Pro52.88
11GPT Image 152.5
12Qwen-Image-251251.84
13Imagen 4.0 Ultra51.16
14HunyuanImage 3.050.76
15Imagen 4.050.63

Interactive version: theaggregate.ai/benchmark?slug=qwen-image-bench-english-quality · How It Works · Data refreshed daily, snapshot 2026-11-22.