whatmodel.sh / image / Qwen-Image-3.0-Pro
Qwen-Image-3.0-Pro
↗ share
+ contribute
Qwen-Image-3.0-Pro is a closed-weights image model from Alibaba, released July 2026. Licence: proprietary.
Score within the LMArena text-to-image comparison set only.
$ how it compares
The image models ranked either side of Qwen-Image-3.0-Pro, out of 197 with a score, then more from Alibaba.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 9 |  Nano Banana 2 (Gemini 3.1 Flash Image) | 76±1 | api $0.067/image | ||
| 10 | Nano Banana Pro (Gemini 3 Pro Image) | 76±1 | api $0.13/image | ||
| 11 | Qwen-Image-3.0-Pro | 75±2 | api $0.040/image | ||
| 12 |  Seedream 5.0 Pro | 75±2 | api $0.050/image | ||
| 13 |  Reve 2.0 | 74±2 | api $0.25/image | ||
| more from Alibaba | |||||
| 18 | Qwen-Image-2.1 | 69±2 | local | ||
| 20 | Qwen-Image-2.0-Pro (2026-06-22) | 67±2 | api $0.075/image | ||
| 24 | Qwen-Image 2.0 Pro | 66±3 | api $0.075/image | ||
$ what it's good at
text to image▂▅▅▃▄▄█▃▁▃▁▁ #9 of 126 · 98% of its score · 3 tests
Beats Nano Banana Pro (Gemini 3 Pro Image) here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena text-to-image | 1255.2 ✎ | ▂▂▃▄▇█▄▂▄▂·▂ beats 64/75 | 72% |
| GenExam (relaxed overall, GPT-5 judge) | 93.7% ✎ | ▆▆·▂▂····▂▂█ beats 10/13 | 18% |
| UltraText Bench (Composite, bilingual dense text rendering) | 88.3% ✎ | ▁▂▂█▃▁▂▃·▁·▁ beats 18/22 | 8.1% |
$ where to run it
Through an API
api · Alibaba Cloud Model Studio · $0.040/image · www.alibabacloud.com ↗ · price sourceUSD per generated image, 1K output, Singapore (international) deployment; 2K output $0.075/image; each input image $0.003 (none for text-to-image). Beijing and Frankfurt deployments list different rates; limited-time promotions excluded. Product: Alibaba Cloud Model Studio image generation. API model: qwen-image-3.0-pro. Settings: resolution=1K, region=Singapore (international), n=1. Price basis: published list rate. Currency: USD. Alibaba Cloud official model page, observed 2026-09-25.
$ how the score was worked out · LMArena leaderboard dataset 72%, GenExam leaderboard (OpenGVLa… 18%, UltraText Bench: A Comprehens… 8%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 LMArena leaderboard dataset | 1 | 72% |
 GenExam leaderboard (OpenGVLab/GenExam README, relaxed score) | 1 | 18% |
 UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation (arXiv:2610.09823v1) | 1 | 8% |
| prior · pull toward the middle | 2% | |
| weighted average | = 75.4 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json