Text-to-Video Arena

View overall rankings across text to video AI models.

Apr 7, 2026

335,302 votes

38 models

	Rank Spread
1	11	dreamina-seedance-2.0-720p Bytedance · Proprietary	1450±15	2,702
2	29	veo-3.1-audio-1080p Google · Proprietary	1371±16	5,878
3	29	veo-3.1-audio Google · Proprietary	1369±14	13,629
4	29	sora-2-pro OpenAI · Proprietary	1364±8	27,737
5	210	veo-3.1-fast-audio Google · Proprietary	1363±11	39,212
6	211	veo-3.1-fast-audio-1080p Google · Proprietary	1362±17	6,048
7	29	grok-imagine-video-720p xAI · Proprietary	1361±8	71,624
8	211	wan2.6-t2v Alibaba · Proprietary	1349±16	16,769
9	211	veo-3-fast-audio Google · Proprietary	1349±11	25,154
10	611	veo-3-audio Google · Proprietary	1341±12	18,969
11	711	sora-2 OpenAI · Proprietary	1340±8	37,169
12	1217	wan2.5-t2v-preview Alibaba · Proprietary	1266±17	6,790
13	1217	seedance-v1.5-pro Bytedance · Proprietary	1259±7	50,632
14	1217	veo-3 Google · Proprietary	1254±11	14,954
15	1218	veo-3-fast Google · Proprietary	1249±12	15,228
16	1221	runway-gen-4.5 Runway · Proprietary	1242±22	13,216
17	1221	pixverse-v5.6 Pixverse · Proprietary	1238±18	13,243
18	1523	kling-2.5-turbo-1080p KlingAI · Proprietary	1220±17	2,103
19	1622	kling-2.6-pro KlingAI · Proprietary	1218±8	51,304
20	1628	ray-3 Luma AI · Proprietary	1207±22	1,121
21	1629	kling-o1-pro KlingAI · Proprietary	1206±27	1,194
22	1827	hailuo-02-pro MiniMax · Proprietary	1199±12	9,370
23	1927	hailuo-2.3 MiniMax · Proprietary	1197±8	40,563
24	2028	seedance-v1-pro Bytedance · Proprietary	1192±11	12,122
25	2030	p-video Pruna · Proprietary	1185±13	6,412
26	2030	hailuo-02-standard MiniMax · Proprietary	1181±12	9,333
27	2030	kandinsky-5.0-t2v-pro Kandinsky · MIT	1176±21	2,020
28	2230	hunyuan-video-1.5 Tencent · tencent-hunyuan-community	1170±16	4,271
29	2430	veo-2 Google · Proprietary	1164±16	6,511
30	2530	kling-v2.1-master KlingAI · Proprietary	1164±9	14,051
31	3134	wan-v2.2-a14b Alibaba · Apache 2.0	1133±15	10,419
32	3134	ltx-2-19b lightricks · ltx-2-community-license-agreement	1130±10	33,943
33	3134	kandinsky-5.0-t2v-lite Kandinsky · MIT	1115±18	1,475
34	3134	seedance-v1-lite Bytedance · Proprietary	1114±9	16,215
35	3536	sora OpenAI · Proprietary	1070±16	4,080
36	3536	ray2 Luma AI · Proprietary	1066±17	5,217
37	3738	pika-v2.2 Pika · Proprietary	1009±15	5,728
38	3738	mochi-v1 Genmo AI · Apache 2.0	1007±16	5,862

Text-to-Video Arena

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)