LMArena Text-to-Video Arena
Video generation models make clips from the same text prompt, anonymously and side by side. Votes from logged-in users give Elo-style ratings.
Video Arena moved to the web on 2026-01-21 with 15 video models. It ran earlier in another venue, per the blog.
- 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.
Gemini Omni 1.1 Flash leads with 1,516
Best score per entry from the benchmark's own leaderboard, read on 2 Nov 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.
- 1,516
Gemini Omni 1.1 Flash
- 1,513
Gemini Omni Flash
- 1,493 Flux 3 Video
- 1,492 Grok Imagine Video 1.5 Agent
- 1,479
Dreamina Seedance 2.0
- 1,476
Wan 3.0
- 1,474
Dreamina Seedance 2.5
- 1,460
MiniMax H3
- 1,456
Muse Video
- 1,427 HappyHorse 1.0
- 1,368 Sora 2 Pro
- 1,364
Veo 3.1 Audio
- 1,362
Veo 3.1 Fast Audio
- 1,348
Veo 3 Fast Audio
- 1,343 Sora 2
- 1,342 Grok Imagine Video
- 1,340
Veo 3 Audio
- 1,337
Wan 2.7 T2V
- 1,327
Wan 2.6 T2V
- 1,256
Seedance v1.5 Pro
- 1,254
Veo 3
- 1,248
Veo 3 Fast
- 1,245
Wan 2.5 T2V Preview
- 1,240
PixVerse v5.6
- 1,225 Runway Gen-4.5
- 1,220
Kling 2.5 Turbo
- 1,216
Kling 2.6 Pro
- 1,207 p-video
- 1,206 Ray 3
- 1,206
Hailuo 2.3
- 1,205
Kling O1 Pro
- 1,198
Hailuo 02 Pro
- 1,191
Seedance v1 Pro
- 1,181
Hailuo 02 Standard
- 1,175 Kandinsky 5.0 T2V Pro
- 1,169
HunyuanVideo 1.5
- 1,164
Veo 2
- 1,163
Kling v2.1 Master
- 1,154 LTX-2 19B
- 1,132
Wan 2.2 A14B
- 1,113
Seedance v1 Lite
- 1,113 Kandinsky 5.0 T2V Lite
- 1,069 Sora
- 1,065 Ray2
- 1,009 Pika v2.2
- 1,007
Mochi v1
Bars start at 1,000.
- 1
Gemini Omni 1.1 Flash 1,516
- 2
Gemini Omni Flash 1,513
- 3 Flux 3 Video 1,493
- 4 Grok Imagine Video 1.5 Agent 1,492
- 5
Dreamina Seedance 2.0 1,479
- 6
Wan 3.0 1,476
- 7
Dreamina Seedance 2.5 1,474
- 8
MiniMax H3 1,460
- 9
Muse Video 1,456
- 10 HappyHorse 1.0 1,427
- 11 Sora 2 Pro 1,368
- 12
Veo 3.1 Audio 1,364
- 13
Veo 3.1 Fast Audio 1,362
- 14
Veo 3 Fast Audio 1,348
- 15 Sora 2 1,343
- 16 Grok Imagine Video 1,342
- 17
Veo 3 Audio 1,340
- 18
Wan 2.7 T2V 1,337
- 19
Wan 2.6 T2V 1,327
- 20
Seedance v1.5 Pro 1,256
- 21
Veo 3 1,254
- 22
Veo 3 Fast 1,248
- 23
Wan 2.5 T2V Preview 1,245
- 24
PixVerse v5.6 1,240
- 25 Runway Gen-4.5 1,225
- 26
Kling 2.5 Turbo 1,220
- 27
Kling 2.6 Pro 1,216
- 28 p-video 1,207
- 29 Ray 3 1,206
- 30
Hailuo 2.3 1,206
- 31
Kling O1 Pro 1,205
- 32
Hailuo 02 Pro 1,198
- 33
Seedance v1 Pro 1,191
- 34
Hailuo 02 Standard 1,181
- 35 Kandinsky 5.0 T2V Pro 1,175
- 36
HunyuanVideo 1.5 1,169
- 37
Veo 2 1,164
- 38
Kling v2.1 Master 1,163
- 39 LTX-2 19B 1,154
- 40
Wan 2.2 A14B 1,132
- 41
Seedance v1 Lite 1,113
- 42 Kandinsky 5.0 T2V Lite 1,113
- 43 Sora 1,069
- 44 Ray2 1,065
- 45 Pika v2.2 1,009
- 46
Mochi v1 1,007
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 1,516 | Sep 2026 | Official leaderboard | |
| 2 | | 1,513 | Sep 2026 | Official leaderboard | |
| 3 | Flux 3 Video | 1,493 | Sep 2026 | Official leaderboard | |
| 4 | Grok Imagine Video 1.5 Agent | 1,492 | Sep 2026 | Official leaderboard | |
| 5 | | 1,479 | Sep 2026 | Official leaderboard | |
| 6 | | 1,476 | Sep 2026 | Official leaderboard | |
| 7 | | 1,474 | Sep 2026 | Official leaderboard | |
| 8 | | 1,460 | Sep 2026 | Official leaderboard | |
| 9 | | 1,456 | Sep 2026 | Official leaderboard | |
| 10 | HappyHorse 1.0 | 1,427 | Sep 2026 | Official leaderboard | |
| 11 | Sora 2 Pro | 1,368 | Sep 2026 | Official leaderboard | |
| 12 | | 1,364 | Sep 2026 | Official leaderboard | |
| 13 | | 1,362 | Sep 2026 | Official leaderboard | |
| 14 | | 1,348 | Sep 2026 | Official leaderboard | |
| 15 | Sora 2 | 1,343 | Sep 2026 | Official leaderboard | |
| 16 | Grok Imagine Video | 1,342 | Sep 2026 | Official leaderboard | |
| 17 | | 1,340 | Sep 2026 | Official leaderboard | |
| 18 | | 1,337 | Sep 2026 | Official leaderboard | |
| 19 | | 1,327 | Sep 2026 | Official leaderboard | |
| 20 | | 1,256 | Sep 2026 | Official leaderboard | |
| 21 | | 1,254 | Sep 2026 | Official leaderboard | |
| 22 | | 1,248 | Sep 2026 | Official leaderboard | |
| 23 | | 1,245 | Sep 2026 | Official leaderboard | |
| 24 | | 1,240 | Sep 2026 | Official leaderboard | |
| 25 | Runway Gen-4.5 | 1,225 | Sep 2026 | Official leaderboard | |
| 26 | | 1,220 | Sep 2026 | Official leaderboard | |
| 27 | | 1,216 | Sep 2026 | Official leaderboard | |
| 28 | p-video | 1,207 | Sep 2026 | Official leaderboard | |
| 29 | Ray 3 | 1,206 | Sep 2026 | Official leaderboard | |
| 30 | | 1,206 | Sep 2026 | Official leaderboard | |
| 31 | | 1,205 | Sep 2026 | Official leaderboard | |
| 32 | | 1,198 | Sep 2026 | Official leaderboard | |
| 33 | | 1,191 | Sep 2026 | Official leaderboard | |
| 34 | | 1,181 | Sep 2026 | Official leaderboard | |
| 35 | Kandinsky 5.0 T2V Pro | 1,175 | Sep 2026 | Official leaderboard | |
| 36 | | 1,169 | Sep 2026 | Official leaderboard | |
| 37 | | 1,164 | Sep 2026 | Official leaderboard | |
| 38 | | 1,163 | Sep 2026 | Official leaderboard | |
| 39 | LTX-2 19B | 1,154 | Sep 2026 | Official leaderboard | |
| 40 | | 1,132 | Sep 2026 | Official leaderboard | |
| 41 | | 1,113 | Sep 2026 | Official leaderboard | |
| 42 | Kandinsky 5.0 T2V Lite | 1,113 | Sep 2026 | Official leaderboard | |
| 43 | Sora | 1,069 | Sep 2026 | Official leaderboard | |
| 44 | Ray2 | 1,065 | Sep 2026 | Official leaderboard | |
| 45 | Pika v2.2 | 1,009 | Sep 2026 | Official leaderboard | |
| 46 | | 1,007 | Sep 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%