Video editing
Models that restyle, extend or change existing footage, AI-first video editors and clip tools, and node-based pipelines that run open video models locally.
Models are ranked by Artificial Analysis Video Arena: Video Editing (AA-Video-Editing v1.1, with audio), Artificial Analysis Video Arena: Video Editing, no audio (AA-Video-Editing-Silent v1.1), then LMArena (Arena) Video Edit leaderboard for models without a result on the first. Tools inherit the tier of the best model they offer. How we rank.
- Best overallSWan 3.01,200 on Artificial Analysis Video Arena: Video Editing (AA-Video-Editing v1.1, with audio)
- Best valueAMiniMax H3Tier A for $0.08/s of video
- Best free startSFLORAFree tier · from $18/mo · via Wan 3.0
- Best local (≤24 GB GPU)No qualifying option yet
- Tier: how close to the best result on the task's main public benchmark
- Outlined: a tool inherits the tier of the best model it offers
- No public result yet
- Cloud · Local: runs on your own hardware
Models
The engines themselves. Use them through an API or inside the apps on the right.
Apps
Ready-made apps with a UI: sign in or install, then start.
Workflow platforms
Node and canvas tools that chain several models into one pipeline.
Quality vs. price
Artificial Analysis Video Arena: Video Editing (AA-Video-Editing v1.1, with audio) score against API price (USD per second of video, log scale). Up and to the left is better; the line joins the models that nothing else beats on both.
- Closed models
- Open-weights models
- Best-value frontier
Show as table
| Model | Weights | Artificial Analysis Video Arena: Video Editing (AA-Video-Editing v1.1, with audio) | Price | Frontier |
|---|---|---|---|---|
| Wan 3.0 | Closed | 1,200 | $0.2/s of video | Yes |
| Seedance 2.5 | Closed | 1,155 | $0.57/s of video | |
| Gemini Omni Flash 1.1 | Closed | 1,149 | $0.1/s of video | Yes |
| MiniMax H3 | Open | 1,125 | $0.08/s of video | Yes |
| Aleph 2.0 | Closed | 1,014 | $0.28/s of video |
Quality vs. setup
The same tools as the map, placed by how good the results can be (up) and how much setup they take (right). Top-left is the easiest way to top quality; further right buys control, privacy or price at the cost of setup. Models are left out: you reach them through these tools.
- Cloud
- Local: runs on your hardware
- Hollow: tier inherited from the best model the tool offers
Not placed (no public result yet): LTX Desktop, Adobe Premiere (formerly Premiere Pro), Autodesk Flow Studio, Beeble, Captions, DaVinci Resolve, Descript, DomoAI, Eddie AI, Final Cut Pro, Gling, Kapwing, Kdenlive, Kling AI, Microsoft Clipchamp, OpusClip, Pictory, Riverside, Submagic, VEED, Viggle, Vizard, Wondershare Filmora
Everything, in order
| Tier | Name | Approach | Runs | Rated by | Price | Skill |
|---|---|---|---|---|---|---|
| S | Wan 3.0 Alibaba | Models | Cloud | 1,200 on Artificial Analysis Video Arena: Video Editing (AA-Video-Editing v1.1, with audio) | $0.2/s of video | — |
| S | FLORA | Workflow platforms | Cloud | via Wan 3.0 | Free tier · $18/mo | intermediate |
| S | Higgsfield AI | Apps | Cloud | via Wan 3.0 | — | beginner |
| S | invideo | Apps | Cloud | via Wan 3.0 | — | beginner |
| S | Krea | Apps + Workflow platforms | Cloud | via Wan 3.0 | Free tier · $5.25/mo | beginner |
| S | Pika Labs | Apps | Cloud | via Wan 3.0 | Free tier · $10/mo | beginner |
| S | Runway | Apps | Cloud | via Wan 3.0 | Free tier · $15/mo | beginner |
| A | ByteDance (Seed) | Models | Cloud | 1,155 on Artificial Analysis Video Arena: Video Editing (AA-Video-Editing v1.1, with audio) | $0.57/s of video | — |
| A | Google | Models | Cloud | 1,149 on Artificial Analysis Video Arena: Video Editing (AA-Video-Editing v1.1, with audio) | $0.1/s of video | — |
| A | MiniMax | Models | Local | 1,125 on Artificial Analysis Video Arena: Video Editing (AA-Video-Editing v1.1, with audio) | Open weights | — |
| A | ByteDance | Apps | Cloud | via Seedance 2.5 | Free tier | beginner |
| A | Lightricks | Apps | Cloud | via Seedance 2.5 | Free tier · $15/mo | beginner |
| A | Luma AI | Apps | Cloud | via Seedance 2.5 | Free tier · $30/mo | beginner |
| A | Adobe | Apps | Cloud | via Gemini Omni Flash 1.1 | $9.99/mo | beginner |
| A | Comfy Org | Workflow platforms | Local | via MiniMax H3 Cloud models: tier S | Free | advanced |
| A | deepbeepmeep (community project) | Apps | Local | via MiniMax H3 | Free | intermediate |
| C | Runway | Models | Cloud | 1,014 on Artificial Analysis Video Arena: Video Editing (AA-Video-Editing v1.1, with audio) | $0.28/s of video | — |
| – | Lightricks | Apps | Local | No public result yet | Free | intermediate |
| – | Adobe | Apps | Cloud | No public result yet | Free tier · $23/mo | intermediate |
| – | Autodesk | Apps | Cloud | No public result yet | Free tier | beginner |
| – | Beeble | Apps | Local | No public result yet | Free tier · $19/mo | intermediate |
| – | Captions | Apps | Cloud | No public result yet | Free tier · $25/mo | beginner |
| – | Blackmagic Design | Apps | Local | No public result yet | Free tier | intermediate |
| – | Descript | Apps | Cloud | No public result yet | Free tier · $24/mo | beginner |
| – | DomoAI | Apps | Cloud | No public result yet | — | beginner |
| – | Eddie AI | Apps | Cloud | No public result yet | Free tier | intermediate |
| – | Apple | Apps | Local | No public result yet | $13/mo | intermediate |
| – | Black Forest Labs | Models | Cloud | No public result yet | $0.03/s of video | — |
| – | Gling | Apps | Cloud | No public result yet | Free tier · $20/mo | beginner |
| – | xAI | Models | Cloud | No public result yet | $0.08/s of video | — |
| – | JD (jd-opensource) | Models | Local | No public result yet | ~32 GB VRAM | — |
| – | Kapwing | Apps | Cloud | No public result yet | Free tier · $16/mo | beginner |
| – | KDE | Apps | Local | No public result yet | Free | intermediate |
| – | Kuaishou (Kling AI) | Models | Cloud | No public result yet | — | — |
| – | Kuaishou | Apps | Cloud | No public result yet | Free tier | beginner |
| – | Lightricks | Models | Local | No public result yet | Open weights | — |
| – | Lucy 2.5 Decart | Models | Cloud | No public result yet | $0.04/s of video | — |
| – | Decart | Models | Local | No public result yet | Open weights | — |
| – | NTU S-Lab (Peiqing Yang et al.) | Models | Local | No public result yet | Open weights | — |
| – | Microsoft | Apps | Cloud | No public result yet | Free tier | beginner |
| – | OpusClip | Apps | Cloud | No public result yet | Free tier · $15/mo | beginner |
| – | Pictory | Apps | Cloud | No public result yet | $29/mo | beginner |
| – | Luma AI | Models | Cloud | No public result yet | — | — |
| – | Riverside | Apps | Cloud | No public result yet | Free tier · $29/mo | beginner |
| – | Skywork AI (Kunlun Tech) | Models | Local | No public result yet | Open weights | — |
| – | Submagic | Apps | Cloud | No public result yet | $19/mo | beginner |
| – | VEED | Apps | Cloud | No public result yet | Free tier | beginner |
| – | Viggle | Apps | Cloud | No public result yet | Free tier · $7.99/mo | beginner |
| – | Viggle | Models | Local | No public result yet | Open weights | — |
| – | Vizard.ai | Apps | Cloud | No public result yet | Free tier | beginner |
| – | Alibaba (Wan-AI) | Models | Local | No public result yet | ~24 GB VRAM | — |
| – | Alibaba (Wan-AI) | Models | Local | No public result yet | Open weights | — |
| – | Wondershare | Apps | Cloud | No public result yet | Free tier | beginner |
Benchmarks used
- Artificial Analysis Video Arena: Video Editing (AA-Video-Editing v1.1, with audio) by Artificial Analysis (blind human votes, Elo (pairwise human preference)) · snapshot 18 Oct 2026With-audio board: models edit a source video from a text instruction with audio kept; 9 models, Kling 3.0 Omni 1080p (Pro) anchored at 1000; category views Complex Edits, Object Editing, Physics & World Simulation, Sound & Speech Editing, Visual Effects Editing. Only open-weights entry is MiniMax H3; no Luma, Decart Lucy, LTX, Veo, Grok or FLUX entries. Lists older versions (Seedance 2.0, HappyHorse-1.0, Wan 2.7). No last-updated date shown.
- Artificial Analysis Video Arena: Video Editing, no audio (AA-Video-Editing-Silent v1.1) by Artificial Analysis (blind human votes, Elo (pairwise human preference)) · snapshot 18 Oct 2026No-audio view of the AA video editing arena (same page, 'No Audio' toggle); 10 models incl. Kling O1 Pro (January); Kling 3.0 Omni 1080p (Pro) anchored at 1000. No category breakdown in this view. No last-updated date shown.
- LMArena (Arena) Video Edit leaderboard by LMArena (arena.ai) (blind human votes, Arena score (Bradley-Terry Elo-style rating from pairwise votes)) · snapshot 27 Aug 2026Overall category, 10 models (dataset config video_edit, split latest, publish date 2026-08-27; the Video Edit Arena launched March 2026). Includes older versions (dreamina-seedance-2.0-720p, happyhorse-1.0, kling-o1-pro, kling-o3-pro, runway-gen4-aleph, unversioned gemini-omni-flash and grok-imagine-video); lacks Aleph 2.0, Gemini Omni Flash 1.1, Luma, Decart Lucy. url points to the HF dataset, as for the other LMArena records (arena.ai pages returned 403 to earlier researchers).