whatmodel.sh / video / Vidu Q3 Pro

Vidu Q3 Pro

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

Vidu Q3 Pro is a closed-weights video model from ShengShu (Vidu), released January 2026. Licence: proprietary.

65.3±2.0#21 of 93 video modelsfrom 5 benchmark results across 5 sources

$ how it compares

The video models ranked either side of Vidu Q3 Pro, out of 139 with a score, then more from ShengShu (Vidu).

#modelscorewhereRAMreleased
22Kling 3.0 Kuaishou (Kling AI)68±4api $0.084/sec2026-02
23Wan 2.7 Alibaba68±2api $0.10/sec2026-04
24Vidu Q3 Pro ShengShu (Vidu)65±2api $0.10/sec2026-01
25Veo 3 Fast Google65±2comparison only2025-07
26Runway Aleph 2.0 Runway65±7api $0.28/sec2026-05
more from ShengShu (Vidu)
47Vidu Q2 Turbo ShengShu (Vidu)55±3api $0.050/sec2025-09
54Vidu Q2 Pro ShengShu (Vidu)53±3comparison only2025-09
108Vidu 1.5 ShengShu (Vidu)38±3comparison only2024-11

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

$ what it's good at

image to video▁▂·▂▅█▅▄▅▆▃▄ #21 of 50 * · 70% of its score · 2 tests

Beats HappyHorse 1.1 here, though they rank higher overall. Trails Runway Gen-4.5, Kling 2.6 Pro, Wan 2.6 here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Arena image-to-video1363.1 ✎▁▁▁▁▄▇▃▆▃▂▄█ beats 26/40avg 1189▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 44%typical
Rapidata physics realism (I2V, with reference)987.0 ✎▂··▂▂▆█▆▂▂▆▄ beats 3/19avg 741▇▇▇▇▇▇▇▇▇▇ 26%sharp
other tests3 not in a task · 28% of its score
testresultvs the others in its rundifficultycountswhy
Rapidata relative camera movement (I2V, alignment Elo)977.9 ✎█···▄▄██·█▄█ beats 2/12avg 661▇▇▇▇▇▇ 16%sharp · noisy
Rapidata image-to-video realism (overall Elo)1083.2 ✎▂······▃▂▃▃█ beats 1/12avg 871▇▇▇ 8.5%sharp · noisy
Datapoint Video Bench (overall Elo)953.5 ✎▃▃·▅·▃·▃··▃█ beats 0/9avg 889▇▇ 3.9%blunt

$ where to run it

Through an API

api · Vidu · $0.10/sec · platform.vidu.com ↗ · price sourceUSD per second of generated video, 720P, standard (peak) rate. Product: Vidu API video generation (text2video/img2video/start-end2video). API model: Vidu Q3-pro (viduq3-pro). Settings: resolution=720P, 1–16 s. Price basis: 20 credits/s at $0.005 per credit; Vidu prints $0.1/s. Off-peak $0.05/s; 1080P $0.12/s. Sales tax excluded. Currency: USD. Vidu platform pricing page, observed 2026-09-25.

$ how the score was worked out · LMArena leaderboard dataset 44%, Rapidata/world-model-physics… 26%, Rapidata/relative-camera-move… 16% 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

sourceresultsshare of the scorelicence
LMArena leaderboard dataset1▇▇▇▇▇▇▇▇▇▇▇▇▇ 44%CC BY 4.0
Rapidata/world-model-physics published dataset-card rankings1▇▇▇▇▇▇▇▇ 26%CC-BY-4.0
Rapidata/relative-camera-movement-human-preference-900k published dataset-card rankings1▇▇▇▇▇ 16%CC-BY-4.0
Rapidata/image-to-video-realism published dataset-card rankings1▇▇▇ 9%CC-BY-4.0
Datapoint Video Bench leaderboard (datapointai/text-to-video-human-preferences-326k dataset card)1▇ 4%CC-BY-4.0
prior · pull toward the middle▇ 2%
weighted average= 65.3

$ 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