Image to Video Leaderboard (With Audio)Artificial Analysis

Added to the leaderboard in the last month:

LTX-2.5 Fast, LTX-2.5 Pro, Vidu Q3 Turbo, MiniMax H3, MAGI-2 Preview

Range
Creator
Model
Elo
95% CI
Samples
Released
API Pricing 1
11-2
ByteDance Seed logoByteDance Seed
Dreamina Seedance 2.0 720p
1,192-7/715,202Mar 2026$9.07 /min
21-3
MiniMax logoMiniMax
MiniMax H3Hugging FaceOpen Weights
1,185-9/96,555Jul 2026$7.80 /min
32-3
Google logoGoogle
Gemini Omni Flash
1,181-8/89,897May 2026$6.00 /min
44-5
SpaceXAI logoSpaceXAI
grok-imagine-video-1.5
1,110-8/85,890May 2026$8.40 /min
54-6
Alibaba-ATH logoAlibaba-ATH
HappyHorse-1.1
1,106-7/711,146Jun 2026$9.90 /min
65-6
Sand.ai logoSand.ai
MAGI-2 PreviewHugging FaceOpen Weights
1,099-7/711,460Aug 2026Coming soon
77-10
Alibaba-ATH logoAlibaba-ATH
HappyHorse-1.0
1,085-7/78,383Apr 2026$13.20 /min
87-10
Skywork AI logoSkywork AI
SkyReels V4
1,085-8/85,407Mar 2026$21.00 /min
97-10
Alibaba logoAlibaba
Wan 2.7
1,085-8/85,164Apr 2026$9.00 /min
107-10
Google logoGoogle
Veo 3.1
1,085-7/78,462Jan 2026$24.00 /min
1111-13
SpaceXAI logoSpaceXAI
grok-imagine-video
1,076-6/615,329Jan 2026$4.20 /min
1211-14
Google logoGoogle
Veo 3.1 Fast
1,073-6/614,300Jan 2026$9.00 /min
1311-16
KlingAI logoKlingAI
Kling 3.0 1080p (Pro)
1,071-6/614,892Feb 2026$20.16 /min
1412-16
Google logoGoogle
Veo 3.1 Lite
1,068-7/77,761Mar 2026$4.80 /min
1512-17
PixVerse logoPixVerse
PixVerse V6
1,066-7/79,758Mar 2026$6.90 /min
1613-16
KlingAI logoKlingAI
Kling 3.0 720p (Standard)
1,066-6/614,859Feb 2026$15.60 /min
1717-18
Vidu logoVidu
Vidu Q3 Pro
1,060-6/615,203Jan 2026$9.60 /min
1816-18
KlingAI logoKlingAI
Kling 3.0 Omni 1080p (Pro)
1,059-7/77,540Feb 2026$16.80 /min
1919
KlingAI logoKlingAI
Kling 3.0 Omni 720p (Standard)
1,049-7/77,471Feb 2026$13.44 /min
2019-21
Lightricks logoLightricks
LTX-2.5 FastHugging FaceOpen Weights
1,040-10/102,376Aug 2026$7.80 /min
2120-21
Vidu logoVidu
Vidu Q3 Turbo
1,037-9/92,920Feb 2026$3.90 /min
2222-23
Lightricks logoLightricks
LTX-2.5 ProHugging FaceOpen Weights
1,014-10/102,298Aug 2026$10.20 /min
2323-24
KlingAI logoKlingAI
Kling 2.6 Pro (January)
1,004-7/77,828Jan 2026$8.40 /min
2424
ByteDance Seed logoByteDance Seed
Seedance 1.5 pro
1,0000/010,692Dec 2025$11.86 /min
2525-27
PixVerse logoPixVerse
PixVerse V5.6
959-8/86,395Feb 2026Coming soon
2625-27
Lightricks logoLightricks
LTX-2.3 FastHugging FaceOpen Weights
956-7/710,153Mar 2026$2.40 /min
2725-27
Lightricks logoLightricks
LTX-2.3 ProHugging FaceOpen Weights
952-7/710,180Mar 2026$4.80 /min
2828-29
Lightricks logoLightricks
LTX-2 FastHugging FaceOpen Weights
930-8/85,995Oct 2025$2.40 /min
2928-29
Sapiens AI logoSapiens AI
Agnes-Video-V2.0
922-9/95,564May 2026$0.30 /min
3030
Alibaba logoAlibaba
Wan 2.6
893-8/86,273Dec 2025$9.00 /min
3131
Lightricks logoLightricks
LTX-2 ProHugging FaceOpen Weights
872-9/95,882Oct 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

Dreamina Seedance 2.0 720p currently leads among Image to Video models with audio output in the Artificial Analysis Image to Video Arena with an Elo score of 1192.

The top Image to Video models with audio by Elo rating are: 1. Dreamina Seedance 2.0 720p (Elo 1192), 2. MiniMax H3 (Elo 1185), 3. Gemini Omni Flash (Elo 1181), 4. grok-imagine-video-1.5 (Elo 1110), 5. HappyHorse-1.1 (Elo 1106). 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 1185, followed by MAGI-2 Preview (Elo 1099) and LTX-2.5 Fast (Elo 1040).

Gemini Omni Flash currently leads the Artificial Analysis Image to Video Arena (without audio) with an Elo score of 1365.

The top Image to Video models without audio by Elo rating are: 1. Gemini Omni Flash (Elo 1365), 2. MiniMax H3 (Elo 1346), 3. Dreamina Seedance 2.0 720p (Elo 1337), 4. grok-imagine-video-1.5 (Elo 1328), 5. grok-imagine-video (Elo 1325). 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 1263) and Cosmos3-Super-Image2Video (Elo 1244).

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