whatmodel.sh / video / Runway Gen-2

Runway Gen-2

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

Runway Gen-2 is a closed-weights video model from Runway, released June 2023. Licence: proprietary.

Catalogue identity notes

Introduced March 2023, public release June 2023; not offered in Runway's current API (Gen-3 Alpha Turbo and later).

26.6±1.9comparison only: no current run option verifiedfrom 7 benchmark results across 3 sources

$ how it compares

The video models ranked either side of Runway Gen-2, out of 139 with a score, then more from Runway.

#modelscorewhereRAMreleased
129DynamiCrafter (1024) CUHK / Tencent AI Lab (DynamiCrafter)27±4comparison only2024-02
130Open-Sora 1.2 HPC-AI Tech27±3local~39GB2024-06
131Runway Gen-2 Runway27±2comparison only2023-06
132PikaLab (September 2023) Pika27±2comparison only2023-09
133VideoCrafter1 T2V Tencent AI Lab / HKUST26±2local~8.1GB2023-10
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

text to video▇▅▄▆█▆▇▂▃▃▂▄ #84 of 94 · 98% of its score · 7 tests

Beats ZeroScope v2 576w, Open-Sora 1.2 here, though they rank higher overall.

testresultvs the others in its rundifficultycountswhy
EvalCrafter 2023 motion quality56.43 / 100 ✎▄····▄██··▄▄ beats 7/7very easy · avg 85.14 / 100▇▇▇▇▇▇▇ 18%at its level
VideoPhy (human, SA=1 & PC=1)7.6% ✎▄▄▄·▄▄█····▄ beats 0/7medium · avg 48%▇▇▇▇▇▇▇ 18%sharp
EvalCrafter 2023 visual quality62.51 / 100 ✎▄█·····▄·█▄▄ beats 7/7very easy · avg 87.87 / 100▇▇▇▇▇▇▇ 17%at its level
EvalCrafter 2023 temporal consistency64.41 / 100 ✎▄···▄▄▄▄▄··█ beats 6/7very easy · avg 88.67 / 100▇▇▇▇▇▇▇ 17%at its level
EvalCrafter 2023 text-video alignment60.98 / 100 ✎▂··▂▂·····▃█ beats 3/7very easy · avg 87.86 / 100▇▇▇▇▇▇ 15%at its level
VideoPhy (auto-evaluator average)29.0% ✎▅·▃▅··▃█···▃ beats 0/9medium · avg 56%▇▇▇ 7.5%at its level
ChronoMagic-Bench-150 GPT4o-MTScore (time-lapse metamorphosis)52.4% ✎▄·▄█▄▄▄·▄·▄█ beats 5/10medium · avg 71%▇▇ 6.2%at its level

$ where to run it

No verified API or download recorded yet · add one

$ how the score was worked out · EvalCrafter: original 2023 te… 67%, VideoPhy / VideoPhy-2 officia… 25%, ChronoMagic-Bench: A Benchmar… 6%

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
EvalCrafter: original 2023 text-to-video evaluations4▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 67%CC-BY-4.0
VideoPhy / VideoPhy-2 official repository leaderboards2▇▇▇▇▇▇▇▇ 25%MIT
ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation1▇▇ 6%CC-BY-4.0
prior · pull toward the middle▇ 2%
weighted average= 26.6

$ 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