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 Image-to-videoData Sep 22, 2026
MiniMax H3MiniMax · 1495

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 · Image-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 PPika V2.2Pika 997±14 48 8,635 – – – Proprietary
2 Runway Gen-4 TurboRunway 1052±13 47 6,801 – – – Proprietary
3 Ray 2Luma AI 1108±16 46 9,521 – – – Proprietary
4 LLTX 2 19BLightricksOpen 1159±5 45 262,336 – – – ltx-2-community-license-agreement
5 Veo 2Google 1166±16 44 10,303 1099±11 63 Dec 2024 Proprietary
6 Wan V2.2 A14BAlibabaOpen 1170±10 43 27,054 – – – Apache 2.0
7 Seedance V1 LiteByteDance 1185±8 42 33,734 – – – Proprietary
8 Hailuo 02 FastMiniMax 1194±11 41 22,519 1207±11 44 Jun 2025 Proprietary
9 Hunyuan Video 1.5TencentOpen 1198±16 40 5,462 1134±11 59 Nov 2025 tencent-hunyuan-community
10 SVidu Q2 ProShengshu (Vidu) 1223±17 39 2,614 1233±10 37 Sep 2025 Proprietary
11 Hailuo 02 StandardMiniMax 1224±10 38 21,785 1246±11 32 Jun 2025 Proprietary
12 Ray 3Luma AI 1226±19 37 1,585 1215±10 41 Sep 2025 Proprietary
13 Hailuo 02 ProMiniMax 1229±11 35 21,743 1249±11 31 Jun 2025 Proprietary
14 Kling V2.1 StandardKling (Kuaishou) 1229±8 36 29,957 – – – Proprietary
15 Kling V2.1 MasterKling (Kuaishou) 1235±8 34 29,824 – – – Proprietary
16 PP-Video 1244±16 32 23,364 1130±11 60 Feb 2026 Proprietary
17 SVidu Q2 TurboShengshu (Vidu) 1244±17 33 2,509 1236±10 35 Sep 2025 Proprietary
18 Veo 3 FastGoogle 1257±10 31 26,272 – – – Proprietary
19 Veo 3Google 1258±10 30 26,081 1225±10 39 Jul 2025 Proprietary
20 Hailuo 2.3MiniMax 1262±5 29 405,786 1255±9 28 Oct 2025 Proprietary
21 Seedance V1 ProByteDance 1273±8 28 34,019 – – – Proprietary
22 Kling 2.5 Turbo 1080pKling (Kuaishou) 1276±13 27 3,795 1298±9 11 Sep 2025 Proprietary
23 Kling 2.6 ProKling (Kuaishou) 1294±8 26 202,113 1266±9 22 Jan 2026 Proprietary
24 PPixVerse V5.6PixVerse 1299±7 25 126,710 1287±10 14 Feb 2026 Proprietary
25 Seedance V1.5 ProByteDance 1307±7 24 245,206 – – – Proprietary
26 Wan 2.6 I2VAlibaba 1310±7 23 121,082 – – – Proprietary
27 Wan 2.5 I2V PreviewAlibaba 1321±10 22 16,907 – – – Proprietary
28 Veo 3 Fast AudioGoogle 1326±10 21 41,194 – – – Proprietary
29 Veo 3 AudioGoogle 1331±12 20 32,367 – – – Proprietary
30 Kling V3 ProKling (Kuaishou) 1354±6 19 206,221 – – – Proprietary
31 SVidu Q3 ProShengshu (Vidu) 1363±9 18 36,679 1290±9 13 Jan 2026 Proprietary
32 Veo 3.1 Fast Audio 1080pGoogle 1372±9 17 54,380 – – – Proprietary
33 Veo 3.1 Fast AudioGoogle 1385±9 15 99,804 – – – Proprietary
34 Grok Imagine Video 480pxAI 1385±8 16 19,429 – – – Proprietary
35 Veo 3.1 Audio 1080pGoogle 1390±9 14 53,089 – – – Proprietary
36 Veo 3.1 AudioGoogle 1398±10 13 25,116 – – – Proprietary
37 Grok Imagine Video 720pxAI 1415±4 12 554,050 – – – Proprietary
38 WWan 2.7 I2VWan 1428±5 11 85,521 – – – Proprietary
39 AHappyHorse 1.0Aorizon 1442±10 10 70,640 1294±9 12 Apr 2026 Proprietary
40 FLUX 3 Video (20260811)Black Forest Labs 1449±5 9 37,042 – – – Proprietary
41 HHiDream O1 Video 1.0HiDream 1456±8 7 6,488 – – – Proprietary
42 Grok Imagine Video 1.5 720pxAI 1456±4 8 137,459 1331±11 8 May 2026 Proprietary
43 Gemini Omni FlashGoogle 1465±6 6 87,155 1368±11 1 May 2026 Proprietary
44 Dreamina Seedance 2.0 720pByteDance 1475±7 5 121,427 1339±9 6 Mar 2026 Proprietary
45 Dreamina Seedance 2.5 720pByteDance 1477±7 4 15,729 – – – Proprietary
46 Wan 3.0Alibaba 1480±11 3 3,442 1362±13 3 Aug 2026 Proprietary
47 Gemini Omni 1.1 FlashGoogle 1488±11 2 3,734 – – – Proprietary
48 MiniMax H3MiniMaxOpen 1495±5 1 57,112 1356±11 4 Jul 2026 minimax-h3-community-license-agreement

Scores: LMArena leaderboard-dataset (lmarena-ai on Hugging Face, CC-BY-4.0), Image-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

This week

Collecting data: 1/7 days recorded; weekly changes appear after 7 days

Synced automatically once a day; ranks are compared only between real snapshots, never backfilled.

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.