Skip to content
IFAI

Model rankings

1396 models · 5 boards · 2 sources

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

Text-to-video arena · Anonymous head-to-head votes · Published August 3, 2026

Best video
gemini-omni-flashGoogle1,513Score
Best open model
minimax-h3MiniMax1,455Score
Best from China
dreamina-seedance-2.0-720pByteDance1,479Score
Most voted
grok-imagine-video-720pxAI151,774Votes
Top three by Score
1gemini-omni-flashGoogle1,513
3muse-videoMeta1,458
Top three open models
1minimax-h3MiniMax · #4 overall1,455
2kandinsky-5.0-t2v-proKandinsky · #30 overall1,173
3hunyuan-video-1.5Tencent · #31 overall1,169
This week's changes
muse-spark-1.2 (xHigh)Coding · #13New
gemini-3.5-flash-highCoding · #25New
Inkling SmallIntelligence · #36New
Celeris-1Intelligence · #221New
RankChangeModelScore95% intervalVotes
1—gemini-omni-flashClosedGoogle1,513±1214,571
2—dreamina-seedance-2.0-720pClosedByteDance1,479±1147,067
3—muse-videoClosedMeta1,458±152,160
4Newminimax-h3OpenMiniMax1,455±191,060
5▼ 1happyhorse-1.0ClosedAorizon1,428±1321,979
6▼ 1sora-2-proClosedOpenAI1,365±844,543
7—veo-3.1-audioClosedGoogle1,364±1413,687
8▼ 2veo-3.1-audio-1080pClosedGoogle1,363±1024,846
9▼ 1veo-3.1-fast-audioClosedGoogle1,362±1139,301
10▼ 1veo-3.1-fast-audio-1080pClosedGoogle1,358±1025,637
11▼ 1grok-imagine-video-720pClosedxAI1,349±8151,774
12—veo-3-fast-audioClosedGoogle1,347±1125,154
13▼ 2wan2.7-t2vClosedWan1,347±915,246
14—sora-2ClosedOpenAI1,340±760,178
15▼ 2veo-3-audioClosedGoogle1,339±1318,961
16▼ 1wan2.6-t2vClosedAlibaba1,330±941,706
17▼ 1seedance-v1.5-proClosedByteDance1,256±775,653
18—veo-3ClosedGoogle1,253±1114,947
19▼ 2wan2.5-t2v-previewClosedAlibaba1,252±1025,895
20▼ 1veo-3-fastClosedGoogle1,248±1215,229
21▼ 1pixverse-v5.6Closed1,240±1132,222
22▼ 1runway-gen-4.5ClosedRunway1,221±1136,550
23▼ 1kling-2.5-turbo-1080pClosedKling1,219±172,104
24▼ 1kling-2.6-proClosedKling1,217±772,888
25▼ 1p-videoClosed1,206±167,029
26—ray-3ClosedLuma AI1,205±221,121
27▼ 2kling-o1-proClosedKling1,205±271,193
28▼ 1hailuo-2.3ClosedMiniMax1,202±772,127
29▼ 1hailuo-02-proClosedMiniMax1,198±139,365
30▼ 1seedance-v1-proClosedByteDance1,190±1112,117
31▼ 1hailuo-02-standardClosedMiniMax1,180±129,333
32▼ 1kandinsky-5.0-t2v-proOpenKandinsky1,173±202,018
33▼ 1hunyuan-video-1.5OpenTencent1,169±164,271
34▼ 1veo-2ClosedGoogle1,163±166,509
35▼ 1kling-v2.1-masterClosedKling1,162±1014,049
36▼ 1ltx-2-19bOpen1,149±961,861
37▼ 1wan-v2.2-a14bOpenAlibaba1,132±1510,418
38▼ 1kandinsky-5.0-t2v-liteOpenKandinsky1,113±181,475
39▼ 1seedance-v1-liteClosedByteDance1,112±1016,211
40▼ 1soraClosedOpenAI1,069±164,080
41▼ 1ray2ClosedLuma AI1,064±175,215
42▼ 1pika-v2.2ClosedPika1,008±155,728
43▼ 1mochi-v1OpenGenmo1,006±175,860

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 “—”.