Image to Video Leaderboard (With Audio)Artificial Analysis

Added to the leaderboard in the last month:

Minimax H3 Max (post-trained by fal), Agnes-Video-2.5, LTX-2.5 Fast, LTX-2.5 Pro, Wan 3.0

Range
Creator
Model
Elo
95% CI
Samples
Released
API Pricing 1
11-2
Fal logoFal
Minimax H3 Max (post-trained by fal)
1200-9/95,608Aug 2026$2.40 /min
22-3
ByteDance Seed logoByteDance Seed
Dreamina Seedance 2.0 720p
1192-6/618,138Mar 2026$9.07 /min
32-4
MiniMax logoMiniMax
MiniMax H3Hugging FaceOpen Weights
1187-8/87,485Jul 2026$7.80 /min
43-5
Google logoGoogle
Gemini Omni Flash
1180-7/712,773May 2026$6.00 /min
54-5
Alibaba logoAlibaba
Wan 3.0
1176-8/87,809Aug 2026$12.00 /min
66-7
SpaceXAI logoSpaceXAI
grok-imagine-video-1.5
1110-7/76,473May 2026$8.40 /min
76-8
Alibaba-ATH logoAlibaba-ATH
HappyHorse-1.1
1105-6/614,170Jun 2026$9.90 /min
87-8
Sand.ai logoSand.ai
MAGI-2 PreviewHugging FaceOpen Weights
1100-7/712,059Aug 2026Coming soon
99-12
Alibaba-ATH logoAlibaba-ATH
HappyHorse-1.0
1087-7/78,943Apr 2026$13.20 /min
109-12
Google logoGoogle
Veo 3.1
1087-7/78,943Jan 2026$24.00 /min
119-12
Skywork AI logoSkywork AI
SkyReels V4
1085-7/75,998Mar 2026$21.00 /min
129-13
Alibaba logoAlibaba
Wan 2.7
1083-7/75,703Apr 2026$9.00 /min
1313-16
SpaceXAI logoSpaceXAI
grok-imagine-video
1077-6/617,880Jan 2026$4.20 /min
1413-18
Google logoGoogle
Veo 3.1 Fast
1073-6/616,818Jan 2026$9.00 /min
1513-18
KlingAI logoKlingAI
Kling 3.0 1080p (Pro)
1072-6/617,285Feb 2026$20.16 /min
1613-18
Google logoGoogle
Veo 3.1 Lite
1071-7/78,210Mar 2026$4.80 /min
1714-18
PixVerse logoPixVerse
PixVerse V6
1069-7/710,192Mar 2026$6.90 /min
1814-18
KlingAI logoKlingAI
Kling 3.0 720p (Standard)
1068-6/617,240Feb 2026$15.60 /min
1919-20
Vidu logoVidu
Vidu Q3 Pro
1061-6/617,521Jan 2026$9.60 /min
2019-20
KlingAI logoKlingAI
Kling 3.0 Omni 1080p (Pro)
1060-7/77,943Feb 2026$16.80 /min
2121
KlingAI logoKlingAI
Kling 3.0 Omni 720p (Standard)
1052-7/77,913Feb 2026$13.44 /min
2221-23
Lightricks logoLightricks
LTX-2.5 FastHugging FaceOpen Weights
1045-9/92,834Aug 2026$7.80 /min
2323-24
Sapiens AI logoSapiens AI
Agnes-Video-2.5
1036-8/86,109Aug 2026$1.50 /min
2423-24
Vidu logoVidu
Vidu Q3 Turbo
1035-8/83,372Feb 2026$3.90 /min
2525
Lightricks logoLightricks
LTX-2.5 ProHugging FaceOpen Weights
1012-9/92,664Aug 2026$10.20 /min
2626-27
KlingAI logoKlingAI
Kling 2.6 Pro (January)
1002-7/78,096Jan 2026$8.40 /min
2727
ByteDance Seed logoByteDance Seed
Seedance 1.5 pro
10000/012,123Dec 2025$11.86 /min
2828-29
PixVerse logoPixVerse
PixVerse V5.6
960-7/76,591Feb 2026Coming soon
2928-30
Lightricks logoLightricks
LTX-2.3 FastHugging FaceOpen Weights
954-7/711,212Mar 2026$2.40 /min
3028-30
Lightricks logoLightricks
LTX-2.3 ProHugging FaceOpen Weights
953-7/711,114Mar 2026$4.80 /min
3131
Lightricks logoLightricks
LTX-2 FastHugging FaceOpen Weights
931-8/86,069Oct 2025$2.40 /min
3232
Sapiens AI logoSapiens AI
Agnes-Video-V2.0
922-8/85,833May 2026$0.30 /min
3333
Alibaba logoAlibaba
Wan 2.6
895-8/86,444Dec 2025$9.00 /min
3434
Lightricks logoLightricks
LTX-2 ProHugging FaceOpen Weights
871-9/95,951Oct 2025$3.60 /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

Minimax H3 Max (post-trained by fal) currently leads among Image to Video models with audio output in the Artificial Analysis Image to Video Arena with an Elo score of 1200.

The top Image to Video models with audio by Elo rating are: 1. Minimax H3 Max (post-trained by fal) (Elo 1200), 2. Dreamina Seedance 2.0 720p (Elo 1192), 3. MiniMax H3 (Elo 1187), 4. Gemini Omni Flash (Elo 1180), and 5. Wan 3.0 (Elo 1176). Rankings are based on blind user votes in the Artificial Analysis Video Arena.

MiniMax H3 currently leads among open weights Image to Video models with audio in the Artificial Analysis Image to Video Arena with an Elo score of 1187, followed by MAGI-2 Preview (Elo 1100) and LTX-2.5 Fast (Elo 1045).

Gemini Omni Flash currently leads the Artificial Analysis Image to Video Arena (without audio) with an Elo score of 1363.

The top Image to Video models without audio by Elo rating are: 1. Gemini Omni Flash (Elo 1363), 2. Wan 3.0 (Elo 1358), 3. MiniMax H3 (Elo 1346), 4. Dreamina Seedance 2.0 720p (Elo 1339), and 5. grok-imagine-video-1.5 (Elo 1328). Rankings are based on blind user votes in the Artificial Analysis Video Arena.

MiniMax H3 currently leads among open weights Image to Video models without audio in the Artificial Analysis Image to Video Arena with an Elo score of 1346, followed by Cosmos3-Super-Image2Video-4Step (Elo 1262) and Cosmos3-Super-Image2Video (Elo 1242).

Text to Video models generate videos from text descriptions alone, while Image to Video models take an existing image as input and animate or extend it into a video. This allows for more control over the visual content and style of the generated video.

Models are ranked using an Elo rating system derived from user votes in blind comparisons. Users compare videos generated from the same input image and choose the result they prefer. Higher Elo scores indicate a model is preferred more often. Vote in the Artificial Analysis Video Arena