whatmodel.sh / video / Wan 2.5 Preview
Wan 2.5 Preview
↗ share
+ contribute
Wan 2.5 Preview is a closed-weights video model from Alibaba, released September 2025.
Model information sources
$ how it compares
The video models ranked either side of Wan 2.5 Preview, out of 139 with a score, then more from Alibaba.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 31 |  Kling O3 Pro | 64±4 | api $0.11/sec | ||
| 32 |  Seedance 1.0 Pro Fast | 62±11 | api $0.049/sec | ||
| 33 | Wan 2.5 Preview | 61±2 | api $0.10/sec | ||
| 34 | Kling 2.6 Pro | 59±2 | api $0.070/sec | ||
| 35 |  PixVerse V5.6 | 59±2 | api $0.045/sec | ||
| more from Alibaba | |||||
| 2 | Wan 3.0 Prime | 80±7 | api $0.14/sec | ||
| 4 | Wan 3.0 | 79±2 | api $0.10/sec | ||
| 9 | HappyHorse 1.1 | 76±3 | api $0.14/sec | ||
$ what it's good at
text to video▆▄▃▄▆▅█▃▂▂▂▄ #17 of 68 * · 45% of its score · 2 tests
Trails Seedance 1.5 Pro here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena video | 1245.3 ✎ | ▂▂▃▆█▆·▆▅▁▂▇ beats 22/41 | 41% |
| VABench T2AV micro Visual QA | 79.3% ✎ | ▄····▄····▄█ beats 2/4 | 4.0% |
image to video▁▂·▂▅█▅▄▅▆▃▄ #24 of 50 · 54% of its score · 4 tests
Trails Runway Gen-4.5, PixVerse V5.6, Kling 2.6 Pro here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena image-to-video | 1321.4 ✎ | ▁▁▁▁▄▇▃▆▃▂▄█ beats 22/40 | 27% |
| Rapidata physics realism (I2V, with reference) | 918.0 ✎ | ▂··▃▂▆█▆▂▂▆▄ beats 1/19 | 15% |
| Target-Bench v2 (VGGT planning score, I2V) | 21.5% ✎ | ▃·▃···▃▃█·▃▃ beats 6/8 | 8.0% |
| VWG-Bench think-with-video reasoning (overall) | 55.0% ✎ | █··▄······▄█ beats 0/5 | 4.1% |
$ where to run it
Through an API
api · Alibaba Cloud Model Studio · $0.10/sec · www.alibabacloud.com ↗ · price sourceUSD per second of output video, 720P, International deployment (Singapore). Product: Model Studio Wan text-to-video. API model: wan2.5-t2v-preview. Settings: resolution=720P. Price basis: published list price; only output is billed. 480P $0.05/s, 1080P $0.15/s. Free quota and other regions excluded. Currency: USD. Alibaba Cloud Model Studio pricing page, observed 2026-09-25.
$ how the score was worked out · LMArena leaderboard dataset 67%, Rapidata/world-model-physics… 15%, Target-Bench: Can Video World… 8% and 2 more
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 | 2 | 67% |
 Rapidata/world-model-physics published dataset-card rankings | 1 | 15% |
 Target-Bench: Can Video World Models Achieve Mapless Path Planning with Semantic Targets? | 1 | 8% |
| From Evaluation to Enhancement: Benchmarking and Improving Think-with-Video Reasoning for Video Generative Models (VWG-Bench) | 1 | 4% |
| VABench: A Comprehensive Benchmark for Audio-Video Generation (arXiv:2512.09299v2) | 1 | 4% |
| prior · pull toward the middle | 1% | |
| weighted average | = 60.5 |
$ 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