---
title: "Image to video leaderboard"
description: "Rankings of image-to-video models."
canonical: https://pirouter.ai/rankings/i2v
last-updated: 2026-10-15
---

# Image to video leaderboard

> Rankings of image-to-video models.

- Updated: 2026-09-22
- 3,475,795 votes · 48 models
- Score · higher is better

## Full ranking

| Rank | Rank spread | Model | Vendor | Score | Votes |
|---|---|---|---|---|---|
| 1 | 1–3 | Minimax H3 | MiniMax | 1495 ±5 | 57112 |
| 2 | 1–5 | Gemini Omni 1.1 Flash | Google | 1489 ±11 | 3734 |
| 3 | 1–6 | Wan3.0 | Alibaba | 1480 ±11 | 3442 |
| 4 | 2–6 | Dreamina Seedance 2.5 720p | ByteDance | 1477 ±7 | 15729 |
| 5 | 2–6 | Dreamina Seedance 2.0 720p | ByteDance | 1475 ±7 | 121427 |
| 6 | 3–8 | Gemini Omni Flash | Google | 1465 ±6 | 87155 |
| 7 | 6–10 | Hidream O1 Video 1.0 | HiDream | 1457 ±8 | 6488 |
| 8 | 6–9 | Grok Imagine Video 1.5 720p | xAI | 1456 ±4 | 137459 |
| 9 | 7–10 | Flux 3 Video | Black Forest Labs | 1449 ±5 | 37042 |
| 10 | 8–11 | Happyhorse 1.0 | Aorizon | 1442 ±10 | 70640 |
| 11 | 10–11 | Wan2.7 I2v | Wan | 1428 ±5 | 85521 |
| 12 | 12–12 | Grok Imagine Video 720p | xAI | 1415 ±4 | 554050 |
| 13 | 13–16 | Veo 3.1 Audio | Google | 1398 ±11 | 25116 |
| 14 | 13–16 | Veo 3.1 Audio 1080p | Google | 1390 ±9 | 53089 |
| 15 | 13–17 | Veo 3.1 Fast Audio | Google | 1385 ±9 | 99804 |
| 16 | 13–17 | Grok Imagine Video 480p | xAI | 1385 ±8 | 19429 |
| 17 | 15–18 | Veo 3.1 Fast Audio 1080p | Google | 1372 ±10 | 54380 |
| 18 | 17–19 | Vidu Q3 Pro | Shengshu | 1363 ±9 | 36679 |
| 19 | 18–19 | Kling V3 Pro | Kling | 1354 ±6 | 206221 |
| 20 | 20–22 | Veo 3 Audio | Google | 1332 ±12 | 32367 |
| 21 | 20–22 | Veo 3 Fast Audio | Google | 1326 ±10 | 41194 |
| 22 | 20–24 | Wan2.5 I2v Preview | Alibaba | 1321 ±10 | 16907 |
| 23 | 22–25 | Wan2.6 I2v | Alibaba | 1310 ±7 | 121082 |
| 24 | 22–26 | Seedance V1.5 Pro | ByteDance | 1307 ±7 | 245206 |
| 25 | 23–26 | Pixverse V5.6 | — | 1299 ±7 | 126710 |
| 26 | 24–27 | Kling 2.6 Pro | Kling | 1294 ±8 | 202113 |
| 27 | 26–31 | Kling 2.5 Turbo 1080p | Kling | 1276 ±13 | 3795 |
| 28 | 27–31 | Seedance V1 Pro | ByteDance | 1273 ±8 | 34019 |
| 29 | 27–33 | Hailuo 2.3 | MiniMax | 1262 ±5 | 405786 |
| 30 | 27–33 | Veo 3 | Google | 1258 ±10 | 26081 |
| 31 | 27–33 | Veo 3 Fast | Google | 1257 ±10 | 26272 |
| 32 | 29–39 | P Video | — | 1244 ±16 | 23364 |
| 33 | 29–39 | Vidu Q2 Turbo | Shengshu | 1244 ±17 | 2509 |
| 34 | 32–39 | Kling V2.1 Master | Kling | 1235 ±8 | 29824 |
| 35 | 32–39 | Hailuo 02 Pro | MiniMax | 1229 ±11 | 21743 |
| 36 | 32–39 | Kling V2.1 Standard | Kling | 1229 ±8 | 29957 |
| 37 | 32–40 | Ray 3 | Luma | 1226 ±19 | 1585 |
| 38 | 32–39 | Hailuo 02 Standard | MiniMax | 1224 ±10 | 21785 |
| 39 | 32–40 | Vidu Q2 Pro | Shengshu | 1223 ±17 | 2614 |
| 40 | 38–42 | Hunyuan Video 1.5 | Tencent | 1198 ±16 | 5462 |
| 41 | 40–42 | Hailuo 02 Fast | MiniMax | 1194 ±11 | 22519 |
| 42 | 40–44 | Seedance V1 Lite | ByteDance | 1185 ±8 | 33734 |
| 43 | 42–45 | Wan V2.2 A14b | Alibaba | 1170 ±10 | 27054 |
| 44 | 42–45 | Veo 2 | Google | 1166 ±16 | 10303 |
| 45 | 43–45 | Ltx 2 19b | — | 1159 ±5 | 262336 |
| 46 | 46–46 | Ray2 | Luma | 1109 ±16 | 9521 |
| 47 | 47–47 | Runway Gen4 Turbo | Runway | 1052 ±13 | 6801 |
| 48 | 48–48 | Pika V2.2 | Pika | 997 ±14 | 8635 |

## FAQ

### What is the best AI model for image to video?

As of 2026-09-22, MiniMax Minimax H3 is #1 on the image to video board with a score of 1495, rank spread 1–3.

### What is the best open-weights model for image to video?

Minimax H3 (MiniMax), #1 on this board.

### What does this board rank?

Rankings of image-to-video models.

### How often is it updated?

Whenever new models ship or the rankings change; this board was last updated on 2026-09-22.

Data: [LMArena leaderboard dataset](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset), used under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/); filtered and reasoning tiers merged, scores unchanged.
View the original board: https://arena.ai/leaderboard/image-to-video