LMArena Video Edit Arena
Wan 3.0 1,414 leads since Aug 2026 Not in model cards Video editing models apply the same edit request to the same clip, anonymously and side by side. Community votes give Elo-style ratings.
Launch month not found. Ratings are in the video_edit config of the dataset.
- Level
- Everyday Most adults, without training
- Scored
- Ranked by votes People pick the better of two answers, as in an arena, and the votes are turned into ratings.
- Answers
- Open-ended Free-form text, documents, designs or media judged as a whole.
Wan 3.0 leads with 1,414 among models released by Aug 2026
Best score per model from the benchmark's own leaderboard, read on 2 Nov 2026. Where a model ran with several settings or harnesses, we keep its best.
The newest model with a score here came out in Aug 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6 Astra
- Claude Opus 5.5
- GPT-6.1 Terra
- GPT-6.1 Sol
- and 16 more
Bars start at 1,150.
- 1 Wan 3.0 1,414
- 2
Dreamina Seedance 2.5 1,410 - 3
MiniMax H3 1,392 - 4
Gemini Omni Flash 1,367 - 5 Dreamina Seedance 2.0 1,365
- 6 HappyHorse 1.0 1,307
- 7 Grok Imagine Video 1,258
- 8
Kling O3 Pro 1,255 - 9 Kling O1 Pro 1,197
- 10 Runway Gen-4 Aleph 1,182
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Wan 3.0 | 1,414 | Aug 2026 | Official leaderboard | |
| 2 | Dreamina Seedance 2.5 | 1,410 | Aug 2026 | Official leaderboard | |
| 3 | MiniMax H3 | 1,392 | Aug 2026 | Official leaderboard | |
| 4 | Gemini Omni Flash | 1,367 | Aug 2026 | Official leaderboard | |
| 5 | Dreamina Seedance 2.0 | 1,365 | Aug 2026 | Official leaderboard | |
| 6 | HappyHorse 1.0 | 1,307 | Aug 2026 | Official leaderboard | |
| 7 | Grok Imagine Video | 1,258 | Aug 2026 | Official leaderboard | |
| 8 | Kling O3 Pro | 1,255 | Aug 2026 | Official leaderboard | |
| 9 | Kling O1 Pro | 1,197 | Aug 2026 | Official leaderboard | |
| 10 | Runway Gen-4 Aleph | 1,182 | Aug 2026 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
No lab model card reports it yet
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark.
More in Audio and video
- Video-MMMU In use 300 expert-level lecture videos with questions testing perception, comprehension and adaptation of knowledge. Accuracy.
Qwen 3.8 Max 88.7% - LVBench In use Hours-long video understanding with multiple-choice questions on reasoning, grounding and summarization. Gemini 4 Argon 91.7%
- MMVU In use 3,000 expert-annotated questions on videos across 27 disciplines. Multiple-choice and open-ended accuracy. Qwen 3.8 Max 82.4%
- MLVU In use Multi-task long video understanding (minutes to hours) with multiple-choice and generation tasks. Accuracy. Qwen 3.8 Max 90.8%
- VoiceBench In use Spoken instructions with speaker, environment and content variation. Voice assistant responses scored by GPT judge or rules. Qwen3.5-Omni-Plus 93.1%
- TVBench In use Models answer multiple-choice questions on 10 temporal video tasks, such as action counting and ordering, that static frames cannot solve. Scored by accuracy. Qwen 3.8 Max 81.9%