Text to Video Leaderboard (With Audio)Artificial Analysis

Added to the leaderboard in the last month:

Vidu Q3 Turbo, MiniMax H3

Range
Creator
Model
Elo
95% CI
Samples
Released
API Pricing 1
11-2
Google logoGoogle
Gemini Omni Flash
1,242-7/712,017May 2026$6.00 /min
21-2
MiniMax logoMiniMax
MiniMax H3Hugging FaceOpen Weights
1,237-9/96,940Jul 2026$7.80 /min
33
ByteDance Seed logoByteDance Seed
Dreamina Seedance 2.0 720p
1,224-6/618,667Mar 2026$9.07 /min
44
Alibaba logoAlibaba
Wan2.7-260612
1,161-7/712,647Jun 2026$9.00 /min
55
Alibaba-ATH logoAlibaba-ATH
HappyHorse-1.1
1,148-7/712,861Jun 2026$9.90 /min
66
Alibaba-ATH logoAlibaba-ATH
HappyHorse-1.0
1,126-7/78,589Apr 2026$13.20 /min
77-9
Alibaba logoAlibaba
Wan 2.7
1,110-8/85,031Apr 2026$9.00 /min
87-9
KlingAI logoKlingAI
Kling 3.0 1080p (Pro)
1,109-6/617,033Feb 2026$20.16 /min
97-10
Skywork AI logoSkywork AI
SkyReels V4
1,107-7/75,537Mar 2026$21.00 /min
109-10
KlingAI logoKlingAI
Kling 3.0 720p (Standard)
1,101-6/616,348Feb 2026$15.12 /min
1111-15
Google logoGoogle
Veo 3.1
1,092-7/78,603Jan 2026$24.00 /min
1211-15
KlingAI logoKlingAI
Kling 3.0 Omni 1080p (Pro)
1,091-7/78,395Feb 2026$16.80 /min
1311-15
Google logoGoogle
Veo 3.1 Fast
1,091-6/615,393Jan 2026$9.00 /min
1411-15
KlingAI logoKlingAI
Kling 3.0 Omni 720p (Standard)
1,090-7/78,213Feb 2026$13.44 /min
1511-15
Google logoGoogle
Veo 3.1 Lite
1,088-7/78,033Mar 2026$4.80 /min
1616-17
Vidu logoVidu
Vidu Q3 Pro
1,079-6/615,579Jan 2026$9.60 /min
1716-17
PixVerse logoPixVerse
PixVerse V6
1,078-7/79,837Mar 2026$6.90 /min
1818
SpaceXAI logoSpaceXAI
grok-imagine-video
1,066-6/614,874Jan 2026$4.20 /min
1919-20
Vidu logoVidu
Vidu Q3 Turbo
1,034-11/112,058Feb 2026$3.90 /min
2020
Alibaba logoAlibaba
Wan 2.6
1,026-7/77,080Dec 2025$9.00 /min
2121
ByteDance Seed logoByteDance Seed
Seedance 1.5 pro
1,0000/010,330Dec 2025$11.86 /min
2222
KlingAI logoKlingAI
Kling 2.6 Pro (January)
988-7/77,844Jan 2026$8.40 /min
2323
Lightricks logoLightricks
LTX-2.3 FastHugging FaceOpen Weights
980-7/710,527Mar 2026$2.40 /min
2424
Lightricks logoLightricks
LTX-2.3 ProHugging FaceOpen Weights
960-7/710,182Mar 2026$4.80 /min
2525-26
PixVerse logoPixVerse
PixVerse V5.6
951-8/86,534Feb 2026Coming soon
2625-26
Lightricks logoLightricks
LTX-2 FastHugging FaceOpen Weights
945-8/86,224Oct 2025$2.40 /min
2727-28
Lightricks logoLightricks
LTX-2 ProHugging FaceOpen Weights
921-8/86,228Oct 2025$3.60 /min
2827-28
Sapiens AI logoSapiens AI
Agnes-Video-V2.0
914-9/94,847May 2026$0.30 /min

1 API Pricing reflects the cost to generate 1 minute of 1080p video on the model creator's API at the model's default settings

Frequently Asked Questions

Gemini Omni Flash currently leads among Text to Video models with audio output in the Artificial Analysis Text to Video Arena with an Elo score of 1242.

The top Text to Video models with audio by Elo rating are: 1. Gemini Omni Flash (Elo 1242), 2. MiniMax H3 (Elo 1237), 3. Dreamina Seedance 2.0 720p (Elo 1224), 4. Wan2.7-260612 (Elo 1161), 5. HappyHorse-1.1 (Elo 1148). Rankings are based on blind user votes in the Artificial Analysis Video Arena.

MiniMax H3 currently leads among open weights Text to Video models with audio in the Artificial Analysis Text to Video Arena with an Elo score of 1237, followed by LTX-2.3 Fast (Elo 980) and LTX-2.3 Pro (Elo 960).

Gemini Omni Flash currently leads the Artificial Analysis Text to Video Arena (without audio) with an Elo score of 1323.

The top Text to Video models without audio by Elo rating are: 1. Gemini Omni Flash (Elo 1323), 2. MiniMax H3 (Elo 1303), 3. HappyHorse-1.0 (Elo 1283), 4. Dreamina Seedance 2.0 720p (Elo 1264), 5. HappyHorse-1.1 (Elo 1261). Rankings are based on blind user votes in the Artificial Analysis Video Arena.

MiniMax H3 currently leads among open weights Text to Video models without audio in the Artificial Analysis Text to Video Arena with an Elo score of 1303, followed by LTX-2.3 Fast (Elo 1122) and LTX-2 Pro (Elo 1121).

Models are ranked using an Elo rating system derived from user votes in blind comparisons in the Artificial Analysis Video Arena. Users compare two videos generated from the same text prompt without knowing which model created each video. Higher Elo scores indicate a model is preferred more often. Vote in the Artificial Analysis Video Arena