For frontier AI news

Text-to-Video Arena

Compare models according to their ability to generate videos based on the given prompt
Generate videos and vote in the Discord server

Last Updated

Dec 12, 2025

Total Votes

106,254

Total Models

26

Rank Spread
(Upper-Lower)
1
1◄─►4
1383±146,373
Google
Proprietary
2
1◄─►4
1374±156,220
Google
Proprietary
3
1◄─►5
1361±1223,616
Google
Proprietary
4
1◄─►6
1356±175,466
OpenAI
Proprietary
5
3◄─►6
1346±1217,134
Google
Proprietary
6
4◄─►6
1325±166,195
OpenAI
Proprietary
7
7◄─►7
1290±172,198
Alibaba
Proprietary
8
8◄─►11
1254±1213,330
Google
Proprietary
9
8◄─►11
1253±1212,954
Google
Proprietary
10
8◄─►13
1238±191,105
KlingAI
Proprietary
11
8◄─►16
1222±221,720
KlingAI
Proprietary
12
10◄─►17
Luma
1208±221,099
Luma AI
Proprietary
13
11◄─►16
Minimax
1207±124,037
MiniMax
Proprietary
14
10◄─►17
1205±211,008
Kandinsky
MIT
15
11◄─►18
1195±1310,102
MiniMax
Proprietary
16
11◄─►19
1187±1412,363
Bytedance
Proprietary
17
13◄─►19
1180±1310,141
MiniMax
Proprietary
18
15◄─►19
1172±1114,686
KlingAI
Proprietary
19
16◄─►19
1163±147,271
Google
Proprietary
20
20◄─►22
1126±1411,430
Alibaba
Apache 2.0
21
20◄─►22
1122±1115,937
Bytedance
Proprietary
22
20◄─►22
1121±181,387
Kandinsky
MIT
23
23◄─►24
1065±134,614
OpenAI
Proprietary
24
23◄─►24
Luma
1063±165,764
Luma AI
Proprietary
25
25◄─►26
1007±146,635
Pika
Proprietary
26
25◄─►26
997±156,813
Genmo AI
Apache 2.0

Remove Style Control Leaderboard Plots

Battle Count for Each Combination of Models (without Ties)

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

Confidence Intervals on Model Strength (via Bootstrapping)

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