Best AI Video Generators: Video Model Leaderboard

Ranked by LMArena scores from anonymous head-to-head human votes. Artificial Analysis Video Arena Elo is shown for comparison; the two scales use different baselines and cannot be compared directly.

Text-to-video Image-to-video
🏆 #1 Text-to-videoData Sep 22, 2026
Gemini Omni 1.1 FlashGoogle · 1516

On LMArena’s text-to-video leaderboard published Sep 22, 2026, #1 is Gemini Omni 1.1 Flash by Google (1516, 1,784 votes); the image-to-video leader is MiniMax H3 (1495).

Full leaderboard · Text-to-video

48 models
All Open weights

Sorted by LMArena score by default; ± is half the 95% confidence interval.

# Model LMArena Artificial Analysis Released License
Score Rank Votes Elo Rank
1 Gemini Omni 1.1 FlashGoogle 1516±15 1 1,784 1069±17 8 Aug 2026 Proprietary
2 Gemini Omni FlashGoogle 1513±9 2 26,576 – – – Proprietary
3 FLUX 3 VideoBlack Forest Labs 1493±17 3 1,302 1093±18 6 Jul 2026 Proprietary
4 Grok Imagine Video 1.5 AgentxAI 1492±18 4 1,218 – – – Proprietary
5 Dreamina Seedance 2.0 720pByteDance 1479±8 5 56,318 1082±18 7 Mar 2026 Proprietary
6 Wan 3.0Alibaba 1476±13 6 2,598 1135±18 2 Aug 2026 Proprietary
7 Dreamina Seedance 2.5 720pByteDance 1474±9 7 8,001 1105±18 5 Jul 2026 Proprietary
8 MiniMax H3MiniMaxOpen 1460±9 8 11,417 1122±18 3 Jul 2026 minimax-h3-community-license-agreement
9 Muse VideoMeta 1456±15 9 2,188 – – – Proprietary
10 AHappyHorse 1.0Aorizon 1427±13 10 22,264 1034±18 12 Apr 2026 Proprietary
11 Sora 2 ProOpenAI 1368±7 11 54,167 – – – Proprietary
12 Veo 3.1 AudioGoogle 1364±14 12 13,741 – – – Proprietary
13 Veo 3.1 Audio 1080pGoogle 1362±10 13 25,076 – – – Proprietary
14 Veo 3.1 Fast AudioGoogle 1362±10 14 39,484 – – – Proprietary
15 Veo 3.1 Fast Audio 1080pGoogle 1358±10 15 25,870 – – – Proprietary
16 Veo 3 Fast AudioGoogle 1348±11 16 25,258 – – – Proprietary
17 Sora 2OpenAI 1343±6 17 71,947 – – – Proprietary
18 Grok Imagine Video 720pxAI 1342±6 18 165,462 – – – Proprietary
19 Veo 3 AudioGoogle 1340±13 19 19,002 – – – Proprietary
20 WWan 2.7 T2VWan 1337±7 20 27,626 – – – Proprietary
21 Wan 2.6 T2VAlibaba 1327±7 21 54,050 – – – Proprietary
22 Seedance V1.5 ProByteDance 1256±7 22 76,171 – – – Proprietary
23 Veo 3Google 1254±11 23 15,005 – – – Proprietary
24 Veo 3 FastGoogle 1248±12 24 15,283 – – – Proprietary
25 Wan 2.5 T2V PreviewAlibaba 1245±9 25 36,378 – – – Proprietary
26 PPixVerse V5.6PixVerse 1240±11 26 32,434 – – – Proprietary
27 Runway Gen-4.5Runway 1225±8 27 48,127 910±18 24 Dec 2025 Proprietary
28 Kling 2.5 Turbo 1080pKling (Kuaishou) 1220±17 28 2,111 – – – Proprietary
29 Kling 2.6 ProKling (Kuaishou) 1216±7 29 73,362 – – – Proprietary
30 PP-Video 1207±16 30 7,079 802±19 32 Feb 2026 Proprietary
31 Ray 3Luma AI 1206±22 31 1,136 – – – Proprietary
32 Hailuo 2.3MiniMax 1206±6 32 89,138 – – – Proprietary
33 Kling O1 ProKling (Kuaishou) 1205±27 33 1,194 890±18 27 Jan 2026 Proprietary
34 Hailuo 02 ProMiniMax 1198±13 34 9,399 – – – Proprietary
35 Seedance V1 ProByteDance 1191±11 35 12,164 – – – Proprietary
36 Hailuo 02 StandardMiniMax 1181±12 36 9,379 – – – Proprietary
37 KKandinsky 5.0 T2V ProKandinskyOpen 1175±21 37 2,019 – – – MIT
38 Hunyuan Video 1.5TencentOpen 1169±16 38 4,292 – – – tencent-hunyuan-community
39 Veo 2Google 1164±16 39 6,531 – – – Proprietary
40 Kling V2.1 MasterKling (Kuaishou) 1163±10 40 14,104 – – – Proprietary
41 LLTX 2 19BLightricksOpen 1154±8 41 75,596 – – – ltx-2-community-license-agreement
42 Wan V2.2 A14BAlibabaOpen 1132±15 42 10,458 – – – Apache 2.0
43 Seedance V1 LiteByteDance 1113±10 43 16,253 – – – Proprietary
44 KKandinsky 5.0 T2V LiteKandinskyOpen 1113±18 44 1,474 – – – MIT
45 SoraOpenAI 1069±16 45 4,082 – – – Proprietary
46 Ray 2Luma AI 1065±17 46 5,250 – – – Proprietary
47 PPika V2.2Pika 1009±15 47 5,763 – – – Proprietary
48 GMochi V1GenmoOpen 1007±17 48 5,893 – – – Apache 2.0

Scores: LMArena leaderboard-dataset (lmarena-ai on Hugging Face, CC-BY-4.0), Text-to-video published Sep 22, 2026; AA columns from the Artificial Analysis Video Arena. Please credit the sources when citing.

Sources & methodology

  1. Scores come from LMArena’s text_to_video and image_to_video leaderboards (overall category, latest release): users vote between two anonymous videos and LMArena fits a Bradley–Terry model.
  2. AA values are shown only when the model name (ignoring bracketed variant notes) maps to exactly one row; hover to see the AA entry name. Anything unmatched stays blank (–); nothing is guessed.
  3. Price, clip length, resolution and speed are not provided by LMArena or the AA API, so they are not shown; 720p/1080p in a name is the variant LMArena tested.
  4. Synced daily at 07:10 UTC; public JSON: /api/public/video-leaderboard.php

FAQ

What is the best AI video generator right now?

On LMArena’s text-to-video leaderboard published Sep 22, 2026, #1 is Gemini Omni 1.1 Flash by Google (1516, 1,784 votes); the image-to-video leader is MiniMax H3 (1495).

Which vendors rank highest for video generation?

On the text-to-video board, each vendor's best model ranks: Google Gemini Omni 1.1 Flash (1516, #1), Black Forest Labs FLUX 3 Video (1493, #3), xAI Grok Imagine Video 1.5 Agent (1492, #4), ByteDance Dreamina Seedance 2.0 720p (1479, #5), Alibaba Wan 3.0 (1476, #6).

Which open-weight video models can I run locally?

7 text-to-video models have non-proprietary licenses; the highest is MiniMax H3 (1460, license minimax-h3-community-license-agreement). Community licenses may restrict commercial use; check the license text.

Why do LMArena and AA scores differ so much?

The two platforms use different voters, prompts and baselines, so absolute numbers are not comparable; relative order within one platform is what matters.