Skip to content
IFAI

Model rankings

1388 models · 5 boards · 2 sources

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

Text-to-video arena · Anonymous head-to-head votes · Updated July 31, 2026

Best video
Gemini Omni FlashGoogle1,323Score
Best open model
LTX-2 ProLightricks1,124Score
Best from China
MiniMax H3MiniMax1,305Score
Top three by Score
1Gemini Omni FlashGoogle1,323
2MiniMax H3MiniMax1,305
3HappyHorse-1.0Alibaba-ATH1,284
Top three open models
1LTX-2 ProLightricks · #43 overall1,124
2LTX-2.3 FastLightricks · #44 overall1,123
3LTX-2 FastLightricks · #45 overall1,119
This week's changes
claude-opus-5-maxCoding · #1New
Reve 2.1Image · #2New
MiniMax H3Video · #2New
qwen3.8-maxCoding · #4New
RankChangeModelScore95% interval
1—Gemini Omni FlashClosedGoogle1,323±10
2—Veo 3.1 PreviewClosedGoogle1,214±8
3—Runway Gen-4.5ClosedRunway1,214±7
4▲ 1Veo 3ClosedGoogle1,214±8
5▼ 1Veo 3 PreviewClosedGoogle1,213±8
6—Veo 3.1 Fast PreviewClosedGoogle1,212±8
7—Veo 3.1 LiteClosedGoogle1,207±8
8▲ 1Veo 3.1 FastClosedGoogle1,201±8
9▼ 1Veo 3.1ClosedGoogle1,201±8
10—Sora 2 ProClosedOpenAI1,181±8
11—Veo 3 Fast PreviewClosedGoogle1,174±8
12—Sora 2 (December)ClosedOpenAI · 1 more variant1,169±9
13—Veo 2ClosedGoogle1,114±8
14—SoraClosedOpenAI1,042±8
15—Motion 2.0ClosedLeonardo.Ai1,011±10
16—Runway Gen 3 AlphaClosedRunway983±8

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 “—”.