Image to Video Leaderboard (With Audio)Artificial Analysis
HiDream-O1-Video, Minimax H3 Max (post-trained by fal), Agnes-Video-2.5
Range | Creator | Model | Elo | 95% CI | Samples | Released | API Pricing 1 | |
|---|---|---|---|---|---|---|---|---|
| 1 | 1 |  Fal | Minimax H3 Max (post-trained by fal) | 1195 | -10/10 | 5,569 | Aug 2026 | $2.40 /min |
| 2 | 2-5 |  MiniMax | MiniMax H3  Open Weights | 1181 | -8/8 | 6,949 | Jul 2026 | $7.80 /min |
| 3 | 2-5 |  Google | Gemini Omni Flash | 1177 | -8/8 | 10,079 | May 2026 | $6.00 /min |
| 4 | 2-5 |  HiDream | HiDream-O1-Video | 1176 | -11/11 | 2,815 | Aug 2026 | $5.80 /min |
| 5 | 3-5 |  ByteDance Seed | Dreamina Seedance 2.0 720p | 1174 | -7/7 | 13,797 | Mar 2026 | $9.07 /min |
| 6 | 6 |  Alibaba | Wan 3.0 | 1164 | -9/9 | 7,761 | Aug 2026 | $12.00 /min |
| 7 | 7-8 | Alibaba-ATH | HappyHorse-1.1 | 1106 | -7/7 | 11,636 | Jun 2026 | $9.90 /min |
| 8 | 7-9 |  SpaceXAI | grok-imagine-video-1.5 | 1099 | -8/8 | 4,861 | May 2026 | $8.40 /min |
| 9 | 8-9 |  Sand.ai | MAGI-2 Preview Open Weights | 1096 | -7/7 | 11,640 | Aug 2026 | Coming soon |
| 10 | 10-12 | Alibaba-ATH | HappyHorse-1.0 | 1083 | -8/8 | 7,177 | Apr 2026 | $13.20 /min |
| 11 | 10-12 | Google | Veo 3.1 | 1082 | -7/7 | 6,738 | Jan 2026 | $24.00 /min |
| 12 | 10-14 | Alibaba | Wan 2.7 | 1078 | -8/8 | 4,260 | Apr 2026 | $9.00 /min |
| 13 | 12-16 |  PixVerse | PixVerse V6 | 1073 | -7/7 | 6,790 | Mar 2026 | $6.90 /min |
| 14 | 12-16 | SpaceXAI | grok-imagine-video | 1073 | -7/7 | 13,828 | Jan 2026 | $4.20 /min |
| 15 | 13-17 |  Skywork AI | SkyReels V4 | 1070 | -8/8 | 4,335 | Mar 2026 | $21.00 /min |
| 16 | 13-17 | Google | Veo 3.1 Lite | 1069 | -8/8 | 4,880 | Mar 2026 | $4.80 /min |
| 17 | 15-17 | Google | Veo 3.1 Fast | 1065 | -7/7 | 12,962 | Jan 2026 | $9.00 /min |
| 18 | 18-20 |  Vidu | Vidu Q3 Pro | 1057 | -7/7 | 13,796 | Jan 2026 | $9.60 /min |
| 19 | 18-20 |  KlingAI | Kling 3.0 1080p (Pro) | 1055 | -7/7 | 13,420 | Feb 2026 | $20.16 /min |
| 20 | 18-20 | KlingAI | Kling 3.0 720p (Standard) | 1052 | -7/7 | 13,302 | Feb 2026 | $15.60 /min |
| 21 | 20-22 | KlingAI | Kling 3.0 Omni 1080p (Pro) | 1045 | -8/8 | 6,002 | Feb 2026 | $16.80 /min |
| 22 | 21-25 |  Lightricks | LTX-2.5 Fast Open Weights | 1037 | -9/9 | 2,829 | Aug 2026 | $7.80 /min |
| 23 | 22-25 | KlingAI | Kling 3.0 Omni 720p (Standard) | 1035 | -8/8 | 6,059 | Feb 2026 | $13.44 /min |
| 24 | 22-25 |  Sapiens AI | Agnes-Video-2.5 | 1031 | -9/9 | 6,170 | Aug 2026 | $1.50 /min |
| 25 | 22-25 | Vidu | Vidu Q3 Turbo | 1030 | -9/9 | 3,267 | Feb 2026 | $3.90 /min |
| 26 | 26-27 | Lightricks | LTX-2.5 Pro Open Weights | 1005 | -10/10 | 2,733 | Aug 2026 | $10.20 /min |
| 27 | 27 | ByteDance Seed | Seedance 1.5 pro | 1000 | 0/0 | 9,233 | Dec 2025 | $11.86 /min |
| 28 | 28 | KlingAI | Kling 2.6 Pro (January) | 990 | -8/8 | 6,205 | Jan 2026 | $8.40 /min |
| 29 | 29 | PixVerse | PixVerse V5.6 | 962 | -8/8 | 4,495 | Feb 2026 | Coming soon |
| 30 | 30-31 | Lightricks | LTX-2.3 Pro Open Weights | 948 | -8/8 | 7,595 | Mar 2026 | $4.80 /min |
| 31 | 30-31 | Lightricks | LTX-2.3 Fast Open Weights | 947 | -8/8 | 7,694 | Mar 2026 | $2.40 /min |
| 32 | 32-33 | Sapiens AI | Agnes-Video-V2.0 | 925 | -9/9 | 3,937 | May 2026 | $0.30 /min |
| 33 | 32-33 | Lightricks | LTX-2 Fast Open Weights | 923 | -9/9 | 4,403 | Oct 2025 | $2.40 /min |
| 34 | 34 | Alibaba | Wan 2.6 | 887 | -9/9 | 4,767 | Dec 2025 | $9.00 /min |
| 35 | 35 | Lightricks | LTX-2 Pro Open Weights | 862 | -10/10 | 4,296 | Oct 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
The top Image to Video models with audio by Elo rating are: 1. Minimax H3 Max (post-trained by fal) (Elo 1195), 2. MiniMax H3 (Elo 1181), 3. Gemini Omni Flash (Elo 1177), 4. HiDream-O1-Video (Elo 1176), and 5. Dreamina Seedance 2.0 720p (Elo 1174). Rankings are based on blind user votes in the Artificial Analysis Video Arena.
Gemini Omni Flash currently leads the Artificial Analysis Image to Video Arena (without audio) with an Elo score of 1369.
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 1354, followed by Cosmos3-Super-Image2Video-4Step (Elo 1274) and Cosmos3-Super-Image2Video (Elo 1253).
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