Skip to content
IFAI

Model rankings

517 models · 3 boards · 2 sources

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

Text-to-video arena · Anonymous head-to-head votes · Published August 28, 2025

Best video
veo-3-fast-audioGoogle1,401Score
Best open model
wan-v2.2-a14bAlibaba1,145Score
Best from China
hailuo-02-proMiniMax1,257Score
Most voted
veo-3-fast-audioGoogle7,155Votes
Top three by Score
1veo-3-fast-audioGoogle1,401
2veo-3-audioGoogle1,393
3veo-3-fastGoogle1,291
Top three open models
1wan-v2.2-a14bAlibaba · #10 overall1,145
2mochi-v1Genmo · #15 overall1,003
This week's changes
DeepSeek V3.1 (Reasoning)Intelligence · #11New
GLM-4.5V (Reasoning)Intelligence · #45New
LFM2 1.2BIntelligence · #164New
Llama 3.2 Instruct 3BIntelligence · #152Up 26
RankChangeModelScore95% intervalVotes
1—veo-3-fast-audioClosedGoogle1,401±117,155
2—veo-3-audioClosedGoogle1,393±115,344
3—veo-3-fastClosedGoogle1,291±114,589
4—veo-3ClosedGoogle1,284±114,381
5—hailuo-02-proClosedMiniMax1,257±114,589
6—hailuo-02-standardClosedMiniMax1,240±114,351
7—seedance-v1-proClosedByteDance1,211±105,581
8—kling-v2.1-masterClosedKling1,197±104,946
9—veo-2ClosedGoogle1,193±114,238
10—seedance-v1-liteClosedByteDance1,124±115,287
11—soraClosedOpenAI1,093±123,023
12—ray2ClosedLuma AI1,074±123,097
13—pika-v2.2ClosedPika1,007±124,606

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 “—”.