Text-to-Video Arena

View overall rankings across text to video AI models.

Apr 7, 2026

335,302 votes

6 open source models

				Rank Spread
1	27	kandinsky-5.0-t2v-pro Kandinsky · MIT	1176±21	2030	2,020
2	28	hunyuan-video-1.5 Tencent · tencent-hunyuan-community	1170±16	2230	4,271
3	31	wan-v2.2-a14b Alibaba · Apache 2.0	1133±15	3134	10,419
4	32	ltx-2-19b lightricks · ltx-2-community-license-agreement	1130±10	3134	33,943
5	33	kandinsky-5.0-t2v-lite Kandinsky · MIT	1115±18	3134	1,475
6	38	mochi-v1 Genmo AI · Apache 2.0	1007±16	3738	5,862

Remove Style Control Leaderboard Plots

Battle Count for Each Combination of Models (without Ties)

Fraction of Model A Wins for All Non-tied A vs. B Battles

Confidence Intervals on Model Strength (via Bootstrapping)

Average Win Rate Against All Other Models (Uniform Sampling and No Ties)