whatmodel.sh / image / Wan 2.5 Image-to-Image Preview
Wan 2.5 Image-to-Image Preview
↗ share
+ contribute
Wan 2.5 Image-to-Image Preview is a closed-weights image model from Alibaba, released September 2025.
Model information sources
Score within the LMArena text-to-image comparison set only.
$ how it compares
The image models ranked either side of Wan 2.5 Image-to-Image Preview, out of 197 with a score, then more from Alibaba.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 90 |  Kling Image 2.1 | 53±7 | api $0.014/image | ||
| 91 |  Imagen 4 Fast | 53±4 | comparison only | ||
| 92 | Wan 2.5 Image-to-Image Preview | 53±4 | api $0.030/image | ||
| 93 |  MiniMax image-01 | 53±5 | api $0.0035/image | ||
| 94 |  Ideogram 3.0 | 52±2 | api $0.060/image | ||
| more from Alibaba | |||||
| 11 |  Qwen-Image-3.0-Pro | 75±2 | api $0.040/image | ||
| 18 | Qwen-Image-2.1 | 69±2 | local | ||
| 20 | Qwen-Image-2.0-Pro (2026-06-22) | 67±2 | api $0.075/image | ||
$ what it's good at
image to image / editing▁▁·▃▂▃█▃▃▄▁▁ #47 of 62 * · 93% of its score · 1 test
Beats GPT Image 1 Mini, FLUX.1 Kontext [max] here, though they rank higher overall. Trails GLM-Image, FLUX.2 [klein] 4B, Ideogram 3.0 here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena image edit | 1181.1 ✎ | ▂▁▁▂▆▇█▄▆▅▁▂ beats 9/53 | 93% |
$ where to run it
Through an API
api · Alibaba Cloud Model Studio · $0.030/image · www.alibabacloud.com ↗ · price sourceUSD per output image, Singapore (international) deployment; only output is billed; China (Beijing) lists $0.028671. Free quota and promotions excluded. Product: Alibaba Cloud Model Studio image generation. API model: wan2.5-i2i-preview. Settings: region=Singapore (international), n=1. Price basis: published list rate. Currency: USD. Alibaba Cloud official model pricing page, observed 2026-09-26.
$ how the score was worked out · LMArena leaderboard dataset 93%
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 | 93% |
| prior · pull toward the middle | 7% | |
| weighted average | = 52.8 |
$ 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