whatmodel.sh / video / Runway Gen-4

Runway Gen-4

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

Runway Gen-4 is a closed-weights video model from Runway, released March 2025.

Model information sources

Release date ↗

49.7±4.2comparison only: no current run option verifiedfrom 2 benchmark results across 2 sources* thinly tested, treat the rank as provisional

$ how it compares

The video models ranked either side of Runway Gen-4, out of 139 with a score, then more from Runway.

#modelscorewhereRAMreleased
66Luma Dream Machine 1.6 Luma AI50±7comparison only2024-09
67Wan 2.2 A14B Alibaba50±2api $0.080/sec +local~31GB2025-07
68Runway Gen-4 Runway50±4comparison only2025-03
69Veo 2 Google50±2comparison only2025-04
70LTX-2 Lightricks49±2local~120GB2025-10
more from Runway
26Runway Aleph 2.0 Runway65±7api $0.28/sec2026-05
36Runway Gen-4.5 Runway58±2api $0.12/sec2025-12
41Runway Aleph Runway56±5comparison only2025-07

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

$ what it's good at

image to video▁▁▂▂██▄▃▃▄▂▂ #41 of 74 * · 53% of its score · 1 test

Beats Seedance 1.5 Pro, Kling 2.1 Standard, HunyuanVideo 1.5 (I2V) here, though they rank higher overall.

testresultvs the others in its rundifficultycountswhy
SkyReels-Bench I2V (human rating)67.8% ✎▄···▄······█ beats 2/3medium · avg 66%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 53%at its level
other tests1 not in a task · 40% of its score
testresultvs the others in its rundifficultycountswhy
MindWorldBench intention accuracy (I2V mental-state reasoning)18.6% ✎▅·▃▅·█·▃···▃ beats 2/9hard · avg 21%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 40%typical

$ where to run it

No verified API or download recorded yet · add one

$ how the score was worked out · SkyReels-V2: Infinite-length… 53%, MindWorldBench: Evaluating Me… 40%

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
SkyReels-V2: Infinite-length Film Generative Model1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 53%CC-BY-4.0
MindWorldBench: Evaluating Mental-State-to-Behavior Reasoning in Image-to-Video Generation (arXiv:2609.39147v1)1▇▇▇▇▇▇▇▇▇▇▇▇ 40%CC-BY-4.0
prior · pull toward the middle▇▇ 7%
weighted average= 49.7

$ 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