Valumigo

LMArena · Image-to-video

We regularly fetch and display public benchmark data: LMArena user voting rankings, Epoch AI test scores, and OpenRouter usage rankings. Each leaderboard shows both its publication date and the date we retrieved it. These scores are not assigned by this site.

LMArena scores come from people comparing two models' answers side by side and voting for the better one, using an Elo-based system. If score differences fall within the confidence intervals, treat the models as roughly comparable.

How to read this leaderboard

What it measures: A ranking based on votes comparing two videos generated from an input image and a prompt.

How to read the score: A relative score reflecting which videos users preferred. It does not objectively score preservation of the original and motion separately.

Caveats: Compare models directly using the image types and motion conditions you need, such as people or products.

Insights from this ranking

  • The 95% confidence intervals for 1st-place minimax-h3 and 2nd-place gemini-omni-1.1-flash overlap. This aggregation alone does not clearly establish their order.
  • 2 other models have confidence intervals that overlap with the 1st-place model's. Interpret small ranking differences cautiously alongside vote counts.
  • The 1st-place model received 57,112 votes, and this leaderboard includes 48 models.

Image-to-video LMArena

Published 2026-09-22 · Retrieved 2026-10-04

130013501400145015001550
MiniMaxminimax-h3
1495
Googlegemini-omni-1.1-flash
1488
Alibabawan3.0
1480
ByteDancedreamina-seedance-2.5-720p
1477
ByteDancedreamina-seedance-2.0-720p
1475
Googlegemini-omni-flash
1465
Hhidream-o1-video-1.0
1456
xgrok-imagine-video-1.5-720p
1456
Bflux-3-video-20260811
1449
Ahappyhorse-1.0
1442
Alibabawan2.7-i2v
1428
xgrok-imagine-video-720p
1415
Googleveo-3.1-audio
1398
Googleveo-3.1-audio-1080p
1390
Googleveo-3.1-fast-audio
1385
xgrok-imagine-video-480p
1385
Googleveo-3.1-fast-audio-1080p
1372
Svidu-q3-pro
1363
Klingkling-v3-pro
1354
Googleveo-3-audio
1331

Dots show scores; horizontal lines show 95% confidence intervals. Overlapping intervals suggest similar performance. The chart shows only the highest-scoring reasoning setting, such as high or max, for each model. The table shows rankings for all settings.

Top ranking by company

  • MiniMaxMiniMaxminimax-h3#1
  • GoogleGooglegemini-omni-1.1-flash#2
  • AlibabaAlibabawan3.0#3
  • ByteDanceByteDancedreamina-seedance-2.5-720p#4
  • HHidreamhidream-o1-video-1.0#7
  • xxAIgrok-imagine-video-1.5-720p#8
  • BBlack Forest Labsflux-3-video-20260811#9
  • AAorizonhappyhorse-1.0#10
  • AlibabaAlibabawan2.7-i2v#11
View table (top 50)
RankModelDeveloperScore95% confidence intervalVotes
1#1MiniMaxminimax-h3MiniMax14951490–150157,112
2#2Googlegemini-omni-1.1-flashGoogle14881478–14993,734
3#3Alibabawan3.0Alibaba14801469–14913,442
4#4ByteDancedreamina-seedance-2.5-720pByteDance14771470–148515,729
5#5ByteDancedreamina-seedance-2.0-720pByteDance14751468–1482121,427
6#6Googlegemini-omni-flashGoogle14651459–147087,155
7#7Hhidream-o1-video-1.0Hidream14561449–14646,488
8#8xgrok-imagine-video-1.5-720pxAI14561452–1460137,459
9#9Bflux-3-video-20260811Black Forest Labs14491445–145437,042
10#10Ahappyhorse-1.0Aorizon14421432–145170,640
11#11Alibabawan2.7-i2vAlibaba14281423–143385,521
12#12xgrok-imagine-video-720pxAI14151411–1419554,050
13#13Googleveo-3.1-audioGoogle13981388–140925,116
14#14Googleveo-3.1-audio-1080pGoogle13901382–139953,089
15#15Googleveo-3.1-fast-audioGoogle13851376–139499,804
16#16xgrok-imagine-video-480pxAI13851376–139319,429
17#17Googleveo-3.1-fast-audio-1080pGoogle13721362–138154,380
18#18Svidu-q3-proShengshu13631354–137236,679
19#19Klingkling-v3-proKling13541349–1360206,221
20#20Googleveo-3-audioGoogle13311320–134332,367
21#21Googleveo-3-fast-audioGoogle13261317–133641,194
22#22Alibabawan2.5-i2v-previewAlibaba13211311–133216,907
23#23Alibabawan2.6-i2vAlibaba13101303–1316121,082
24#24ByteDanceseedance-v1.5-proByteDance13071300–1314245,206
25#25?pixverse-v5.6?12991292–1307126,710
26#26Klingkling-2.6-proKling12941286–1302202,113
27#27Klingkling-2.5-turbo-1080pKling12761263–12883,795
28#28ByteDanceseedance-v1-proByteDance12731265–128134,019
29#29MiniMaxhailuo-2.3MiniMax12621257–1267405,786
30#30Googleveo-3Google12581248–126826,081
31#31Googleveo-3-fastGoogle12571248–126726,272
32#32?p-video?12441227–126023,364
33#33Svidu-q2-turboShengshu12441227–12602,509
34#34Klingkling-v2.1-masterKling12351227–124329,824
35#35MiniMaxhailuo-02-proMiniMax12291218–123921,743
36#36Klingkling-v2.1-standardKling12291220–123729,957
37#37Lray-3Luma AI12261207–12451,585
38#38MiniMaxhailuo-02-standardMiniMax12241214–123321,785
39#39Svidu-q2-proShengshu12231207–12402,614
40#40Thunyuan-video-1.5Tencent11981182–12135,462
41#41MiniMaxhailuo-02-fastMiniMax11941183–120522,519
42#42ByteDanceseedance-v1-liteByteDance11851178–119333,734
43#43Alibabawan-v2.2-a14bAlibaba11701160–118027,054
44#44Googleveo-2Google11661150–118210,303
45#45?ltx-2-19b?11591154–1164262,336
46#46Lray2Luma AI11081092–11259,521
47#47Rrunway-gen4-turboRunway10521039–10666,801
48#48Ppika-v2.2Pika997983–10118,635

Data: LMArena leaderboard dataset (CC BY 4.0). Changes: Top 50 entries per leaderboard; scores are rounded. https://huggingface.co/datasets/lmarena-ai/leaderboard-datasetCompany logos are trademarks of their respective owners and are used only for identification (icons: Simple Icons).Data: Epoch AI — Capabilities & benchmarking (CC BY 4.0). https://epoch.ai/benchmarksSource: OpenRouter (openrouter.ai/rankings), as of 2026-10-04. Licensed under CC BY 4.0. https://openrouter.ai/rankings