LMArena Image-to-Video Arena
Video generation models animate the same input image with the same prompt, anonymously and side by side. Votes give Elo-style ratings.
Shares votes infrastructure with the Text-to-Video Arena. Launched on the web on 2026-01-21.
- 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.
MiniMax H3 leads with 1,495
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.
- 1,495
MiniMax H3
- 1,488
Gemini Omni 1.1 Flash
- 1,480
Wan 3.0
- 1,477
Dreamina Seedance 2.5
- 1,475
Dreamina Seedance 2.0
- 1,465
Gemini Omni Flash
- 1,456
HiDream-O1-Video 1.0
- 1,456 Grok Imagine Video 1.5
- 1,449 Flux 3 Video
- 1,442 HappyHorse 1.0
- 1,428
Wan 2.7 I2V
- 1,415 Grok Imagine Video
- 1,398
Veo 3.1 Audio
- 1,385
Veo 3.1 Fast Audio
- 1,363
Vidu Q3 Pro
- 1,354
Kling v3 Pro
- 1,331
Veo 3 Audio
- 1,326
Veo 3 Fast Audio
- 1,321
Wan 2.5 I2V Preview
- 1,310
Wan 2.6 I2V
- 1,307
Seedance v1.5 Pro
- 1,299
PixVerse v5.6
- 1,294
Kling 2.6 Pro
- 1,276
Kling 2.5 Turbo
- 1,273
Seedance v1 Pro
- 1,262
Hailuo 2.3
- 1,258
Veo 3
- 1,257
Veo 3 Fast
- 1,244 p-video
- 1,244
Vidu Q2 Turbo
- 1,235
Kling v2.1 Master
- 1,229
Hailuo 02 Pro
- 1,229
Kling v2.1 Standard
- 1,226 Ray 3
- 1,224
Hailuo 02 Standard
- 1,223
Vidu Q2 Pro
- 1,198
HunyuanVideo 1.5
- 1,194
Hailuo 02 Fast
- 1,185
Seedance v1 Lite
- 1,170
Wan 2.2 A14B
- 1,166
Veo 2
- 1,159 LTX-2 19B
- 1,108 Ray2
- 1,052 Runway Gen-4 Turbo
- 997 Pika v2.2
Bars start at 900.
- 1
MiniMax H3 1,495
- 2
Gemini Omni 1.1 Flash 1,488
- 3
Wan 3.0 1,480
- 4
Dreamina Seedance 2.5 1,477
- 5
Dreamina Seedance 2.0 1,475
- 6
Gemini Omni Flash 1,465
- 7
HiDream-O1-Video 1.0 1,456
- 8 Grok Imagine Video 1.5 1,456
- 9 Flux 3 Video 1,449
- 10 HappyHorse 1.0 1,442
- 11
Wan 2.7 I2V 1,428
- 12 Grok Imagine Video 1,415
- 13
Veo 3.1 Audio 1,398
- 14
Veo 3.1 Fast Audio 1,385
- 15
Vidu Q3 Pro 1,363
- 16
Kling v3 Pro 1,354
- 17
Veo 3 Audio 1,331
- 18
Veo 3 Fast Audio 1,326
- 19
Wan 2.5 I2V Preview 1,321
- 20
Wan 2.6 I2V 1,310
- 21
Seedance v1.5 Pro 1,307
- 22
PixVerse v5.6 1,299
- 23
Kling 2.6 Pro 1,294
- 24
Kling 2.5 Turbo 1,276
- 25
Seedance v1 Pro 1,273
- 26
Hailuo 2.3 1,262
- 27
Veo 3 1,258
- 28
Veo 3 Fast 1,257
- 29 p-video 1,244
- 30
Vidu Q2 Turbo 1,244
- 31
Kling v2.1 Master 1,235
- 32
Hailuo 02 Pro 1,229
- 33
Kling v2.1 Standard 1,229
- 34 Ray 3 1,226
- 35
Hailuo 02 Standard 1,224
- 36
Vidu Q2 Pro 1,223
- 37
HunyuanVideo 1.5 1,198
- 38
Hailuo 02 Fast 1,194
- 39
Seedance v1 Lite 1,185
- 40
Wan 2.2 A14B 1,170
- 41
Veo 2 1,166
- 42 LTX-2 19B 1,159
- 43 Ray2 1,108
- 44 Runway Gen-4 Turbo 1,052
- 45 Pika v2.2 997
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 1,495 | Sep 2026 | Official leaderboard | |
| 2 | | 1,488 | Sep 2026 | Official leaderboard | |
| 3 | | 1,480 | Sep 2026 | Official leaderboard | |
| 4 | | 1,477 | Sep 2026 | Official leaderboard | |
| 5 | | 1,475 | Sep 2026 | Official leaderboard | |
| 6 | | 1,465 | Sep 2026 | Official leaderboard | |
| 7 | | 1,456 | Sep 2026 | Official leaderboard | |
| 8 | Grok Imagine Video 1.5 | 1,456 | Sep 2026 | Official leaderboard | |
| 9 | Flux 3 Video | 1,449 | Sep 2026 | Official leaderboard | |
| 10 | HappyHorse 1.0 | 1,442 | Sep 2026 | Official leaderboard | |
| 11 | | 1,428 | Sep 2026 | Official leaderboard | |
| 12 | Grok Imagine Video | 1,415 | Sep 2026 | Official leaderboard | |
| 13 | | 1,398 | Sep 2026 | Official leaderboard | |
| 14 | | 1,385 | Sep 2026 | Official leaderboard | |
| 15 | | 1,363 | Sep 2026 | Official leaderboard | |
| 16 | | 1,354 | Sep 2026 | Official leaderboard | |
| 17 | | 1,331 | Sep 2026 | Official leaderboard | |
| 18 | | 1,326 | Sep 2026 | Official leaderboard | |
| 19 | | 1,321 | Sep 2026 | Official leaderboard | |
| 20 | | 1,310 | Sep 2026 | Official leaderboard | |
| 21 | | 1,307 | Sep 2026 | Official leaderboard | |
| 22 | | 1,299 | Sep 2026 | Official leaderboard | |
| 23 | | 1,294 | Sep 2026 | Official leaderboard | |
| 24 | | 1,276 | Sep 2026 | Official leaderboard | |
| 25 | | 1,273 | Sep 2026 | Official leaderboard | |
| 26 | | 1,262 | Sep 2026 | Official leaderboard | |
| 27 | | 1,258 | Sep 2026 | Official leaderboard | |
| 28 | | 1,257 | Sep 2026 | Official leaderboard | |
| 29 | p-video | 1,244 | Sep 2026 | Official leaderboard | |
| 30 | | 1,244 | Sep 2026 | Official leaderboard | |
| 31 | | 1,235 | Sep 2026 | Official leaderboard | |
| 32 | | 1,229 | Sep 2026 | Official leaderboard | |
| 33 | | 1,229 | Sep 2026 | Official leaderboard | |
| 34 | Ray 3 | 1,226 | Sep 2026 | Official leaderboard | |
| 35 | | 1,224 | Sep 2026 | Official leaderboard | |
| 36 | | 1,223 | Sep 2026 | Official leaderboard | |
| 37 | | 1,198 | Sep 2026 | Official leaderboard | |
| 38 | | 1,194 | Sep 2026 | Official leaderboard | |
| 39 | | 1,185 | Sep 2026 | Official leaderboard | |
| 40 | | 1,170 | Sep 2026 | Official leaderboard | |
| 41 | | 1,166 | Sep 2026 | Official leaderboard | |
| 42 | LTX-2 19B | 1,159 | Sep 2026 | Official leaderboard | |
| 43 | Ray2 | 1,108 | Sep 2026 | Official leaderboard | |
| 44 | Runway Gen-4 Turbo | 1,052 | Sep 2026 | Official leaderboard | |
| 45 | Pika v2.2 | 997 | 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%