Skip to content
IFAI

Model rankings

866 models · 5 boards · 2 sources

Artificial AnalysisText-to-video arenaArenaText-to-video arena

Text-to-video arena · Anonymous head-to-head votes · Published November 8, 2026

Best video
Gemini Omni 1.2 FlashGoogle1,540Score
Best open model
MiniMax H3MiniMax1,456Score
Best from China
Dreamina Seedance 2.0 (720p)ByteDance1,483Score
Most voted
Top three by Score
3gemini-omni-flashGoogle1,509
Top three open models
1MiniMax H3MiniMax · #11 overall1,456
2Kandinsky 5.0 Video ProKandinsky · #35 overall1,175
3HunyuanVideo 1.5Tencent · #36 overall1,168
This week's changes
Gemini 4 Carbon (High)Intelligence · #1New
GPT-6.1 Terra (Max)Intelligence · #6New
Fish Audio Drama 3Speech · #6New
P-Video-2-ProVideo · #11New
AssemblyAI-TTS-1Speech · #14New
RankChangeModelScore95% intervalVotes
1NewGemini Omni 1.2 FlashClosedGoogle1,540±161,714
2▼ 1Gemini Omni 1.1 FlashClosedGoogle1,513±151,790
3▼ 1gemini-omni-flashClosedGoogle1,509±846,890
4▼ 1FLUX 3 VideoClosedBlack Forest Labs1,491±171,314
5NewGrok Imagine Video 1.5ClosedxAI1,488±191,249
6▼ 1Dreamina Seedance 2.0 (720p)ClosedByteDance1,483±872,281
7—Dreamina Seedance 2.5 (720p)ClosedByteDance1,479±825,595
8▼ 2Wan 3.0ClosedAlibaba1,476±123,060
9NewSkyReels V4ClosedSkyreel1,459±181,060
10▼ 1Muse VideoClosedMeta1,457±152,225
11NewMiniMax H3OpenMiniMax1,456±829,442
12▼ 2HappyHorse 1.0ClosedAorizon1,429±1222,898
13▼ 2Sora 2 ProClosedOpenAI1,367±755,962
14NewVeo 3.1 (Audio)ClosedGoogle · 1 more variant1,363±1413,790
15NewVeo 3.1 Fast (Audio)ClosedGoogle · 1 more variant1,361±1040,276
16▲ 6Veo 3 Fast (Audio)ClosedGoogle · 1 more variant1,347±1125,277
17▼ 2Sora 2ClosedOpenAI1,342±673,988
18▼ 2Grok Imagine Video (720p)ClosedxAI1,341±6190,307
19▲ 2Veo 3 (Audio)ClosedGoogle · 1 more variant1,340±1319,032
20NewWan 2.7ClosedAlibaba1,337±748,713
21NewWan 2.6ClosedAlibaba1,323±775,964
22▼ 2Seedance 1.5 ProClosedByteDance1,256±777,987
23NewWan 2.5 PreviewClosedAlibaba1,244±943,112
24—PixVerse V5.6Closed1,238±1033,301
25—Runway Gen-4.5ClosedRunway1,223±865,378
26—Kling 2.5 Turbo (1080p)ClosedKling1,220±172,110
27—Kling 2.6 ProClosedKling1,216±775,018
28—P-VideoClosed1,207±167,318
29NewLuma Ray3ClosedLuma AI1,206±221,136
30—Hailuo 2.3ClosedMiniMax1,205±691,747
31NewKling O1 ProClosedKling1,201±271,210
32—Hailuo 02 ProClosedMiniMax1,199±139,399
33NewSeedance 1.0 ProClosedByteDance1,192±1212,167
34—Hailuo 02 StandardClosedMiniMax1,181±129,379
35NewKandinsky 5.0 Video ProOpenKandinsky1,175±212,020
36NewHunyuanVideo 1.5OpenTencent1,168±164,322
37—Veo 2ClosedGoogle1,165±166,531
38—Kling 2.1 MasterClosedKling1,163±1014,104
39—LTX-2 19BOpen1,156±792,466
40—Wan 2.2 A14BOpenAlibaba1,132±1510,458
41NewSeedance 1.0 LiteClosedByteDance1,113±1016,258
42NewKandinsky 5.0 Video LiteOpenKandinsky1,113±181,472
43—SoraClosedOpenAI1,069±164,082
44NewLuma Ray2ClosedLuma AI1,066±175,250
45—Pika 2.2ClosedPika1,009±155,763
46—Mochi 1OpenGenmo1,007±175,893

Intelligence over time

Each maker's best model at the time on the Artificial Analysis Intelligence Index, by the month it was released.

Gained most · Anthropic +57.2Highest now · Anthropic 64.6Gap between highest and lowest 18.1 ptsTime range Nov 2025 – Nov 2026
64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi

Arena data comes from the leaderboard dataset it publishes on Hugging Face (CC BY 4.0). Only each board's overall leaderboard is used; scores and ranks are unchanged. dataset · CC BY 4.0

Artificial Analysis data comes from its API (artificialanalysis.ai). Scores are unchanged; ranks follow the scores. artificialanalysis.ai

Open or closed follows the license Arena gives; prices and Artificial Analysis intelligence show only where model names match, otherwise “—”.