whatmodel.sh · find the best video models you can run

Best video editing models

A leaderboard of the best video editing models. Wan 3.0 is #1 right now, followed by Dreamina Seedance 2.5 and MiniMax H3. Models are ranked on human votes comparing their video edits. Filter by your computer or budget to find the best one you can use.

10 models · scores combine 1 benchmarks · updated how it works · find a leaderboard · benchmark your machine

Scores use reviewed video editing evaluations only. Compare scores within this task. Models without task measurements are excluded.

Filter by your hardware and budget · reset
+ more
$ terminal

detecting your OS…

Score vs API price

#modeltask score↓where↓speed↓RAM↓get itsources
1Wan 3.0 Alibaba68±9*api $0.10/secwww.alibabacloud.com ↗LMArena leaderboard dataset
2Dreamina Seedance 2.5 ByteDance67±9*api $0.30/secdocs.dev.runwayml.com ↗LMArena leaderboard dataset
3MiniMax H3 MiniMax64±9*api $0.13/sec +local~40GBfal.ai ↗LMArena leaderboard dataset
4Gemini Omni Flash Google59±9*api $0.10/secai.google.dev ↗LMArena leaderboard dataset
5Dreamina Seedance 2.0 ByteDance Seed59±9*api $0.30/secfal.ai ↗LMArena leaderboard dataset
6HappyHorse 1.0 Alibaba-ATH49±9*api $0.14/secreplicate.com ↗LMArena leaderboard dataset
7Grok Imagine Video xAI40±9*api $0.050/secdocs.x.ai ↗LMArena leaderboard dataset
8Kling O3 Pro Kuaishou (Kling AI)39±9*api $0.11/secfal.ai ↗LMArena leaderboard dataset
9Kling O1 Pro Kuaishou (Kling AI)29±9*api $0.11/secreplicate.com ↗LMArena leaderboard dataset
10Runway Aleph Runway26±9*comparison onlyLMArena leaderboard dataset

Includes 1 comparison-only models with no verified API or download · hide them

10 of 10 catalogue models listed here · sources and licences

* new or thinly tested: ranked on too few benchmark results · † only the maker’s own numbers so far · ~RAM is estimated; full context may need more memory