AA-Video-I2V v1.1Artificial Analysis
Ranks video models on animating a source image into video with audio, by Elo from pairwise human preference votes.
3 models added in the last 30 days
MiniMax H3 (768p), Dreamina Seedance 2.5, and Vidu Q4 Preview
AA-Video-I2V v2.0 is coming soon, with a new prompt set aligned with the AA-Video-T2V v2.0 use case and capability taxonomy, 1080p videos on the silent board, and a more comprehensive model selection.
Range | Model | Elo | Samples | Released | API Pricing 1 | |
|---|---|---|---|---|---|---|
| 1 | 1-5 |  MiniMax H3 (768p)  | 1130±1295% interval 1118 to 1142 | 3,335 | Jul 2026 | $5.40 /min |
| 2 | 1-5 |  Vidu Q4 Preview | 1129±1295% interval 1117 to 1141 | 3,894 | Oct 2026 | $5.04 /min |
| 3 | 1-6 |  Gemini Omni Flash 1.1 | 1126±1195% interval 1115 to 1137 | 3,207 | Aug 2026 | $9.12 /min |
| 4 | 1-7 |  Dreamina Seedance 2.5 | 1120±1295% interval 1108 to 1132 | 2,950 | Jul 2026 | $24.60 /min |
| 5 | 2-7 |  Wan 3.0 | 1119±1195% interval 1108 to 1130 | 5,022 | Aug 2026 | $12.00 /min |
| 6 | 3-7 |  MiniMax H3 Max | 1116±1195% interval 1105 to 1127 | 3,285 | Aug 2026 | $5.76 /min |
| 7 | 4-7 | Dreamina Seedance 2.0 | 1113±1295% interval 1101 to 1125 | 2,670 | Mar 2026 | $22.45 /min |
| 8 | 8 |  FLUX 3 | 1082±1195% interval 1071 to 1093 | 4,010 | Jul 2026 | $17.40 /min |
| 9 | 9-10 |  Grok Imagine Video 1.5 | 1061±1195% interval 1050 to 1072 | 3,230 | May 2026 | $15.00 /min |
| 10 | 9-10 | HappyHorse-1.1 | 1057±1195% interval 1046 to 1068 | 4,804 | Jun 2026 | $9.90 /min |
| 11 | 11-13 |  MAGI-2 Preview | 1040±1195% interval 1029 to 1051 | 3,969 | Aug 2026 | Coming soon |
| 12 | 11-15 | HappyHorse-1.0 | 1034±1195% interval 1023 to 1045 | 3,278 | Apr 2026 | $13.20 /min |
| 13 | 11-16 |  SkyReels V4 | 1033±1295% interval 1021 to 1045 | 2,464 | Mar 2026 | $21.00 /min |
| 14 | 12-16 | Veo 3.1 | 1029±1195% interval 1018 to 1040 | 3,295 | Jan 2026 | $24.00 /min |
| 15 | 12-17 | Wan 2.7 | 1025±1295% interval 1013 to 1037 | 2,307 | Apr 2026 | $9.00 /min |
| 16 | 14-18 |  PixVerse V6 | 1022±1195% interval 1011 to 1033 | 3,288 | Mar 2026 | $6.90 /min |
| 17 | 16-18 | Veo 3.1 Fast | 1013±1095% interval 1003 to 1023 | 5,096 | Jan 2026 | $9.00 /min |
| 18 | 16-19 | Vidu Q3 Pro | 1012±1195% interval 1001 to 1023 | 4,937 | Jan 2026 | $9.60 /min |
| 19 | 17-21 |  Kling 3.0 Omni 1080p (Pro) | 1003±1295% interval 991 to 1015 | 2,816 | Feb 2026 | $16.80 /min |
| 20 | 20 | Kling 3.0 1080p (Pro) | 1000AnchorFixed at 1000 as the reference point for this board's Elo scale. | 5,226 | Feb 2026 | $20.16 /min |
| 21 | 19-21 |  LTX-2.5 Fast | 993±1295% interval 981 to 1005 | 2,108 | Aug 2026 | $7.80 /min |
| 22 | 22-23 | Vidu Q3 Turbo | 971±1295% interval 959 to 983 | 2,360 | Feb 2026 | $3.90 /min |
| 23 | 22-23 | LTX-2.5 Pro | 970±1295% interval 958 to 982 | 2,099 | Aug 2026 | $10.20 /min |
| 24 | 24 | LTX-2.3 Pro | 909±1295% interval 897 to 921 | 2,958 | Mar 2026 | $4.80 /min |
| 25 | 25 | LTX-2.3 Fast | 894±1295% interval 882 to 906 | 2,977 | Mar 2026 | $2.40 /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 models on AA-Video-I2V v1.1 by Elo rating are: 1. MiniMax H3 (768p) (Elo 1130), 2. Vidu Q4 Preview (Elo 1129), 3. Gemini Omni Flash 1.1 (Elo 1126), 4. Dreamina Seedance 2.5 (Elo 1120), and 5. Wan 3.0 (Elo 1119). Rankings are based on blind votes from our recruited human panel.
Gemini Omni Flash currently leads AA-Video-I2V-Silent v1.0 with an Elo score of 1368.
MiniMax H3 currently leads among open weights models on AA-Video-I2V-Silent v1.0 with an Elo score of 1356, followed by Cosmos3-Super-Image2Video-4Step (Elo 1275) and Cosmos3-Super-Image2Video (Elo 1253).
Models are ranked using an Elo rating system derived from blind comparisons judged by our recruited human panel. The ratings without audio also include public Video Arena votes cast before 1 January 2026, and the ratings with audio use panel votes alone. Voters 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