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
1,239-7/714,015May 2026$6.00 /min
21-2
MiniMax logoMiniMax
MiniMax H3Hugging FaceOpen Weights
1,237-8/87,658Jul 2026$7.80 /min
33
ByteDance Seed logoByteDance Seed
Dreamina Seedance 2.0 720p
1,222-6/620,610Mar 2026$9.07 /min
44
Alibaba logoAlibaba
Wan2.7-260612
1,157-6/614,656Jun 2026$9.00 /min
55
Alibaba-ATH logoAlibaba-ATH
HappyHorse-1.1
1,146-6/614,838Jun 2026$9.90 /min
66
Alibaba-ATH logoAlibaba-ATH
HappyHorse-1.0
1,121-7/78,830Apr 2026$13.20 /min
77-9
Alibaba logoAlibaba
Wan 2.7
1,109-7/75,267Apr 2026$9.00 /min
87-9
KlingAI logoKlingAI
Kling 3.0 1080p (Pro)
1,107-6/618,371Feb 2026$20.16 /min
97-10
Skywork AI logoSkywork AI
SkyReels V4
1,103-7/75,770Mar 2026$21.00 /min
109-10
KlingAI logoKlingAI
Kling 3.0 720p (Standard)
1,099-6/617,619Feb 2026$15.12 /min
1111-15
Google logoGoogle
Veo 3.1
1,089-7/78,755Jan 2026$24.00 /min
1211-15
Google logoGoogle
Veo 3.1 Fast
1,089-6/616,516Jan 2026$9.00 /min
1311-15
KlingAI logoKlingAI
Kling 3.0 Omni 720p (Standard)
1,088-7/78,380Feb 2026$13.44 /min
1411-15
KlingAI logoKlingAI
Kling 3.0 Omni 1080p (Pro)
1,087-7/78,571Feb 2026$16.80 /min
1511-15
Google logoGoogle
Veo 3.1 Lite
1,087-7/78,195Mar 2026$4.80 /min
1616-17
Vidu logoVidu
Vidu Q3 Pro
1,076-6/616,555Jan 2026$9.60 /min
1716-17
PixVerse logoPixVerse
PixVerse V6
1,074-7/79,966Mar 2026$6.90 /min
1818
SpaceXAI logoSpaceXAI
grok-imagine-video
1,062-6/615,751Jan 2026$4.20 /min
1919-20
Vidu logoVidu
Vidu Q3 Turbo
1,032-10/102,216Feb 2026$3.90 /min
2019-20
Alibaba logoAlibaba
Wan 2.6
1,025-7/77,199Dec 2025$9.00 /min
2121
ByteDance Seed logoByteDance Seed
Seedance 1.5 pro
1,0000/010,764Dec 2025$11.86 /min
2222
KlingAI logoKlingAI
Kling 2.6 Pro (January)
985-7/77,957Jan 2026$8.40 /min
2323
Lightricks logoLightricks
LTX-2.3 FastHugging FaceOpen Weights
976-7/710,853Mar 2026$2.40 /min
2424
Lightricks logoLightricks
LTX-2.3 ProHugging FaceOpen Weights
958-7/710,477Mar 2026$4.80 /min
2525
PixVerse logoPixVerse
PixVerse V5.6
950-7/76,635Feb 2026Coming soon
2625-26
Lightricks logoLightricks
LTX-2 FastHugging FaceOpen Weights
942-8/86,254Oct 2025$2.40 /min
2727-28
Lightricks logoLightricks
LTX-2 ProHugging FaceOpen Weights
918-8/86,257Oct 2025$3.60 /min
2827-28
Sapiens AI logoSapiens AI
Agnes-Video-V2.0
914-8/84,990May 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 1239.

The top Text to Video models with audio by Elo rating are: 1. Gemini Omni Flash (Elo 1239), 2. MiniMax H3 (Elo 1237), 3. Dreamina Seedance 2.0 720p (Elo 1222), 4. Wan2.7-260612 (Elo 1157), 5. HappyHorse-1.1 (Elo 1146). 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 976) and LTX-2.3 Pro (Elo 958).

Gemini Omni Flash currently leads the Artificial Analysis Text to Video Arena (without audio) with an Elo score of 1322.

The top Text to Video models without audio by Elo rating are: 1. Gemini Omni Flash (Elo 1322), 2. MiniMax H3 (Elo 1305), 3. HappyHorse-1.0 (Elo 1284), 4. Dreamina Seedance 2.0 720p (Elo 1265), 5. HappyHorse-1.1 (Elo 1262). 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 1305, followed by LTX-2 Pro (Elo 1121) and LTX-2 Fast (Elo 1120).

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