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
ByteDance Seed logoByteDance Seed
Dreamina Seedance 2.0 720p
1,193-7/715,384Mar 2026$9.07 /min
21-3
MiniMax logoMiniMax
MiniMax H3Hugging FaceOpen Weights
1,184-9/96,591Jul 2026$7.80 /min
32-3
Google logoGoogle
Gemini Omni Flash
1,182-8/810,014May 2026$6.00 /min
44-5
SpaceXAI logoSpaceXAI
grok-imagine-video-1.5
1,108-8/85,866May 2026$8.40 /min
54-6
Alibaba-ATH logoAlibaba-ATH
HappyHorse-1.1
1,106-7/711,090Jun 2026$9.90 /min
65-6
Sand.ai logoSand.ai
MAGI-2 PreviewHugging FaceOpen Weights
1,100-7/711,420Aug 2026Coming soon
77-10
Google logoGoogle
Veo 3.1
1,085-7/78,385Jan 2026$24.00 /min
87-10
Alibaba logoAlibaba
Wan 2.7
1,085-8/85,096Apr 2026$9.00 /min
97-10
Skywork AI logoSkywork AI
SkyReels V4
1,085-8/85,318Mar 2026$21.00 /min
107-10
Alibaba-ATH logoAlibaba-ATH
HappyHorse-1.0
1,084-7/78,314Apr 2026$13.20 /min
1111-13
SpaceXAI logoSpaceXAI
grok-imagine-video
1,076-6/615,132Jan 2026$4.20 /min
1211-14
KlingAI logoKlingAI
Kling 3.0 1080p (Pro)
1,074-6/614,725Feb 2026$20.16 /min
1311-15
Google logoGoogle
Veo 3.1 Fast
1,072-6/614,041Jan 2026$9.00 /min
1412-16
Google logoGoogle
Veo 3.1 Lite
1,068-7/77,654Mar 2026$4.80 /min
1513-18
PixVerse logoPixVerse
PixVerse V6
1,066-7/79,663Mar 2026$6.90 /min
1614-18
KlingAI logoKlingAI
Kling 3.0 720p (Standard)
1,066-6/614,567Feb 2026$15.60 /min
1715-18
KlingAI logoKlingAI
Kling 3.0 Omni 1080p (Pro)
1,060-7/77,458Feb 2026$16.80 /min
1816-18
Vidu logoVidu
Vidu Q3 Pro
1,060-6/614,844Jan 2026$9.60 /min
1919-20
KlingAI logoKlingAI
Kling 3.0 Omni 720p (Standard)
1,050-7/77,345Feb 2026$13.44 /min
2019-21
Lightricks logoLightricks
LTX-2.5 FastHugging FaceOpen Weights
1,043-10/102,223Aug 2026$7.80 /min
2120-21
Vidu logoVidu
Vidu Q3 Turbo
1,040-9/92,811Feb 2026$3.90 /min
2222
Lightricks logoLightricks
LTX-2.5 ProHugging FaceOpen Weights
1,021-10/102,177Aug 2026$10.20 /min
2323-24
KlingAI logoKlingAI
Kling 2.6 Pro (January)
1,005-7/77,739Jan 2026$8.40 /min
2424
ByteDance Seed logoByteDance Seed
Seedance 1.5 pro
1,0000/010,383Dec 2025$11.86 /min
2525-26
PixVerse logoPixVerse
PixVerse V5.6
961-8/86,349Feb 2026Coming soon
2625-27
Lightricks logoLightricks
LTX-2.3 FastHugging FaceOpen Weights
957-7/79,848Mar 2026$2.40 /min
2726-27
Lightricks logoLightricks
LTX-2.3 ProHugging FaceOpen Weights
953-7/79,885Mar 2026$4.80 /min
2828
Lightricks logoLightricks
LTX-2 FastHugging FaceOpen Weights
932-8/85,966Oct 2025$2.40 /min
2929
Sapiens AI logoSapiens AI
Agnes-Video-V2.0
921-9/95,531May 2026$0.30 /min
3030
Alibaba logoAlibaba
Wan 2.6
893-8/86,257Dec 2025$9.00 /min
3131
Lightricks logoLightricks
LTX-2 ProHugging FaceOpen Weights
872-9/95,876Oct 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 1193.

The top Image to Video models with audio by Elo rating are: 1. Dreamina Seedance 2.0 720p (Elo 1193), 2. MiniMax H3 (Elo 1184), 3. Gemini Omni Flash (Elo 1182), 4. grok-imagine-video-1.5 (Elo 1108), 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 1184, followed by MAGI-2 Preview (Elo 1100) and LTX-2.5 Fast (Elo 1043).

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. MiniMax H3 (Elo 1348), 3. Dreamina Seedance 2.0 720p (Elo 1337), 4. grok-imagine-video-1.5 (Elo 1327), 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 1348, followed by Cosmos3-Super-Image2Video-4Step (Elo 1262) 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