whatmodel.sh / video / Wan 2.6

Wan 2.6

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Wan 2.6 is a closed-weights video model from Alibaba, released December 2025.

Model information sources

Release date ↗

64.7±1.4#23 of 93 video modelsfrom 7 benchmark results across 6 sources

$ how it compares

The video models ranked either side of Wan 2.6, out of 139 with a score, then more from Alibaba.

#modelscorewhereRAMreleased
26Runway Aleph 2.0 Runway65±7api $0.28/sec2026-05
27Sora 2 OpenAI65±2comparison only2025-10
28Wan 2.6 Alibaba65±1api $0.10/sec2025-12
29Wan2.1-VACE-14B Alibaba65±7comparison only2025-05
30Veo 3 Google64±2comparison only2025-07
more from Alibaba
2Wan 3.0 Prime Alibaba80±7api $0.14/sec2026-08
4Wan 3.0 Alibaba79±2api $0.10/sec2026-08
9HappyHorse 1.1 Alibaba76±3api $0.14/sec2026-06

see all video models · find the ones that fit your machine

$ what it's good at

text to video▆▄▃▄▆▅█▃▃▂▂▄ #14 of 68 · 36% of its score · 3 tests
testresultvs the others in its rundifficultycountswhy
LMArena video1326.7 ✎▂▂▃▆█▆·▆▅▁▂▇ beats 24/41avg 1147▇▇▇▇▇▇▇▇▇▇▇▇▇ 33%typical
Sci-VBench testmini (expert human rating)50.4% ✎▅·▃█▃·▅▃▅▃▃▃ beats 7/14hard · avg 44%▇ 2.8%blunt · at its level
HumanScore (T2V)84.8% ✎▂··▂··█▄▂··▆ beats 2/11easy · avg 84%▇ 0.8%blunt
image to video▁▂·▂▅█▅▄▅▆▃▄ #19 of 50 · 57% of its score · 3 tests

Beats HappyHorse 1.1, Vidu Q3 Pro here, though they rank higher overall. Trails Runway Gen-4.5 here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
WorldReasonBench human Elo (image+text-to-video world-state prediction)1211.0 ✎▃▃··█··▃▃▃·▃ beats 6/8avg 875▇▇▇▇▇▇▇▇▇ 23%sharp
Arena image-to-video1309.5 ✎▁▁▁▁▄▇▃▆▃▂▄█ beats 21/40avg 1189▇▇▇▇▇▇▇▇▇ 22%typical
Rapidata physics realism (I2V, with reference)1023.0 ✎▂··▂▂▆█▆▂▂▆▄ beats 5/19avg 741▇▇▇▇▇ 12%sharp
other tests1 not in a task · 6.2% of its score
testresultvs the others in its rundifficultycountswhy
MindWorldBench intention accuracy (I2V mental-state reasoning)39.0% ✎▅·▃▅·█·▃···▃ beats 8/9hard · avg 21%▇▇ 6.2%at its level

$ 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: wan2.6-t2v. Settings: resolution=720P. Price basis: published list price; only output is billed. 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 54%, WorldReasonBench: Human-Align… 23%, Rapidata/world-model-physics… 12% and 3 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

sourceresultsshare of the scorelicence
LMArena leaderboard dataset2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 54%CC BY 4.0
WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors (arXiv v1)1▇▇▇▇▇▇▇ 23%CC-BY-4.0
Rapidata/world-model-physics published dataset-card rankings1▇▇▇▇ 12%CC-BY-4.0
MindWorldBench: Evaluating Mental-State-to-Behavior Reasoning in Image-to-Video Generation (arXiv:2609.39147v1)1▇▇ 6%CC-BY-4.0
Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains1▇ 3%CC-BY-4.0
HumanScore: Benchmarking Human Motions in Generated Videos1▇ 1%CC-BY-4.0
prior · pull toward the middle▇ 1%
weighted average= 64.7

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

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