whatmodel.sh / image / Runway Gen-4 Image

Runway Gen-4 Image

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

Runway Gen-4 Image is a closed-weights image model from Runway.

49.6±2.5#83 of 144 image modelsfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

Score within the LMArena text-to-image comparison set only.

$ how it compares

The image models ranked either side of Runway Gen-4 Image, out of 197 with a score.

#modelscorewhereRAMreleased
102GLM-Image Z.ai50±2api $0.015/image +local~39GB2026-01
103Step1X-Edit v1.2 Preview StepFun50±5comparison only2025-09
104Runway Gen-4 Image Runway50±3api $0.050/image
105Lucid Origin Leonardo.Ai49±3api $0.017/image2025-08
106Latent Diffusion text2img-large (LDM-KL-8-G, LAION-400M) CompVis48±15local~7.5GB2022-04

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

$ what it's good at

text to image▂▅▅▃▄▄█▃▁▂▁▁ #69 of 126 * · 97% of its score · 1 test

Beats Recraft V3, GLM-Image here, though they rank higher overall.

testresultvs the others in its rundifficultycountswhy
LMArena text-to-image1024.2 ✎▂▂▃▄▇█▄▂▄▂·▂ beats 11/75avg 1027▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 97%typical

$ where to run it

Through an API

api · $0.050/image · docs.dev.runwayml.com ↗ · price sourceUSD per generated 720p image: Runway lists gen4_image at 5 credits per 720p image (8 credits, $0.08, per 1080p image); credits cost $0.01 each. Product: Runway developer API image generation. API model: gen4_image (not gen4_image_turbo, 2 credits). Settings: 720p, one image. Price basis: 5 credits × $0.01 per credit; sales tax excluded. Currency: USD. Runway official API pricing page, observed 2026-09-26.

$ how the score was worked out · LMArena leaderboard dataset 97%

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 97%CC BY 4.0
prior · pull toward the middle▇ 3%
weighted average= 49.6

$ 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