Model rankings

892 models · 5 boards · 2 sources

Week of December 22, 2025

February 2, 20266 changes January 26, 2026177 changes January 19, 202610 changes January 12, 2026116 changes January 5, 20263 changes December 29, 202513 changes December 22, 20256 changes December 15, 20258 changes December 8, 202520 changes December 1, 202522 changes November 24, 202546 changes November 17, 202514 changes

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

Text-to-video arena · Anonymous head-to-head votes · Published December 12, 2025

Best video

veo-3.1-fast-audioGoogle1,383Score

Best open model

kandinsky-5.0-t2v-proKandinsky1,205Score

Best from China

wan2.5-t2v-previewAlibaba1,290Score

Most voted

veo-3-fast-audioGoogle23,616Votes

Top three by Score

1veo-3.1-fast-audioGoogle1,383

2veo-3.1-audioGoogle1,374

3veo-3-fast-audioGoogle1,361

Top three open models

1kandinsky-5.0-t2v-proKandinsky · #14 overall1,205

2wan-v2.2-a14bAlibaba · #20 overall1,126

3kandinsky-5.0-t2v-liteKandinsky · #22 overall1,121

This week's changes

Gemini 3 Flash Preview (Reasoning)Intelligence · #3New

glm-4.7Coding · #5New

MiMo-V2-Flash (Reasoning)Intelligence · #10New

mimo-v2-flash (non-thinking)Coding · #16New

K2-V2 (high)Intelligence · #67New

All Open Closed

All regions US China

One row per model All variants

SortScore Votes

Rank	Change	Model	Score	95% interval	Votes
1	—	kandinsky-5.0-t2v-proOpenKandinsky	1,205	±21	1,008
2	—	wan-v2.2-a14bOpenAlibaba	1,126	±14	11,430
3	—	kandinsky-5.0-t2v-liteOpenKandinsky	1,121	±18	1,387
4	—	mochi-v1OpenGenmo	997	±15	6,813

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