Valumigo

LMArena · Text-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 video generation ranking based on votes comparing two videos generated from the same text prompt with model names hidden.

How to read the score: A relative score based on votes in which users watch two videos and choose the result they prefer.

Caveats: This score does not separately control for video length, resolution, sound and cost, or measure value for money. Check generation conditions and costs separately.

Insights from this ranking

  • The 95% confidence intervals for 1st-place gemini-omni-1.1-flash and 2nd-place gemini-omni-flash overlap. This aggregation alone does not clearly establish their order.
  • 3 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 1,784 votes, and this leaderboard includes 48 models.

Text-to-video LMArena

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

13201380144015001560
Googlegemini-omni-1.1-flash
1516
Googlegemini-omni-flash
1513
Bflux-3-video
1493
xgrok-imagine-video-1.5-agent
1492
ByteDancedreamina-seedance-2.0-720p
1479
Alibabawan3.0
1476
ByteDancedreamina-seedance-2.5-720p
1474
MiniMaxminimax-h3
1460
Metamuse-video
1456
Ahappyhorse-1.0
1427
Osora-2-pro
1368
Googleveo-3.1-audio
1364
Googleveo-3.1-audio-1080p
1362
Googleveo-3.1-fast-audio
1362
Googleveo-3.1-fast-audio-1080p
1358
Googleveo-3-fast-audio
1348
Osora-2
1343
xgrok-imagine-video-720p
1342
Googleveo-3-audio
1340
Alibabawan2.7-t2v
1337

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

  • GoogleGooglegemini-omni-1.1-flash#1
  • BBlack Forest Labsflux-3-video#3
  • xxAIgrok-imagine-video-1.5-agent#4
  • ByteDanceByteDancedreamina-seedance-2.0-720p#5
  • AlibabaAlibabawan3.0#6
  • MiniMaxMiniMaxminimax-h3#8
  • MetaMetamuse-video#9
  • AAorizonhappyhorse-1.0#10
  • OOpenAIsora-2-pro#11
View table (top 50)
RankModelDeveloperScore95% confidence intervalVotes
1#1Googlegemini-omni-1.1-flashGoogle15161501–15321,784
2#2Googlegemini-omni-flashGoogle15131504–152226,576
3#3Bflux-3-videoBlack Forest Labs14931476–15101,302
4#4xgrok-imagine-video-1.5-agentxAI14921474–15111,218
5#5ByteDancedreamina-seedance-2.0-720pByteDance14791471–148756,318
6#6Alibabawan3.0Alibaba14761464–14892,598
7#7ByteDancedreamina-seedance-2.5-720pByteDance14741465–14828,001
8#8MiniMaxminimax-h3MiniMax14601452–146911,417
9#9Metamuse-videoMeta14561441–14702,188
10#10Ahappyhorse-1.0Aorizon14271415–144022,264
11#11Osora-2-proOpenAI13681361–137554,167
12#12Googleveo-3.1-audioGoogle13641350–137913,741
13#13Googleveo-3.1-audio-1080pGoogle13621352–137325,076
14#14Googleveo-3.1-fast-audioGoogle13621351–137239,484
15#15Googleveo-3.1-fast-audio-1080pGoogle13581348–136825,870
16#16Googleveo-3-fast-audioGoogle13481337–135925,258
17#17Osora-2OpenAI13431336–134971,947
18#18xgrok-imagine-video-720pxAI13421336–1349165,462
19#19Googleveo-3-audioGoogle13401328–135319,002
20#20Alibabawan2.7-t2vAlibaba13371330–134427,626
21#21Alibabawan2.6-t2vAlibaba13271319–133454,050
22#22ByteDanceseedance-v1.5-proByteDance12561249–126376,171
23#23Googleveo-3Google12541242–126515,005
24#24Googleveo-3-fastGoogle12481236–126015,283
25#25Alibabawan2.5-t2v-previewAlibaba12451237–125436,378
26#26?pixverse-v5.6?12401229–125032,434
27#27Rrunway-gen-4.5Runway12251216–123348,127
28#28Klingkling-2.5-turbo-1080pKling12201202–12372,111
29#29Klingkling-2.6-proKling12161210–122373,362
30#30?p-video?12071192–12237,079
31#31Lray-3Luma AI12061184–12281,136
32#32MiniMaxhailuo-2.3MiniMax12061200–121289,138
33#33Klingkling-o1-proKling12051178–12311,194
34#34MiniMaxhailuo-02-proMiniMax11981186–12119,399
35#35ByteDanceseedance-v1-proByteDance11911179–120212,164
36#36MiniMaxhailuo-02-standardMiniMax11811169–11939,379
37#37Kkandinsky-5.0-t2v-proKandinsky11751154–11962,019
38#38Thunyuan-video-1.5Tencent11691153–11854,292
39#39Googleveo-2Google11641148–11816,531
40#40Klingkling-v2.1-masterKling11631153–117314,104
41#41?ltx-2-19b?11541146–116275,596
42#42Alibabawan-v2.2-a14bAlibaba11321116–114710,458
43#43ByteDanceseedance-v1-liteByteDance11131103–112216,253
44#44Kkandinsky-5.0-t2v-liteKandinsky11131095–11301,474
45#45OsoraOpenAI10691053–10854,082
46#46Lray2Luma AI10651048–10835,250
47#47Ppika-v2.2Pika1009994–10245,763
48#48Gmochi-v1Genmo1007990–10235,893

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