---
title: "Image to video: model rankings and source evidence · Undominated.ai"
canonical: https://undominated.ai/rankings/arena-image-to-video/
description: "Image to video ranked by Arena score. Inspect exact model variants, source dates, measurement limits and downloadable evidence."
---

# Image to video: model rankings and source evidence · Undominated.ai

> Image to video ranked by Arena score. Inspect exact model variants, source dates, measurement limits and downloadable evidence.

[All rankings](/rankings/) / Video

# Image to video

Human preference ratings for the overall category of this Arena task. Scores from different boards are not interchangeable.

**48 entries** · Arena score · Higher is better

Source publication: 2026-09-22. Retrieved 2026-11-05.

Source: [Arena (lmarena-ai)](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset) · [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/).

Ranks use confidence bounds. Several models can share a rank; the rows within a shared rank are displayed by score.

Image to video · Arena score

| Significance rank | Model / evaluated variant | Arena score | 95% confidence interval | Votes |
| --- | --- | --- | --- | --- |
| 1 | minimax-h3 minimax | 1,495.41 | 1,490.21 – 1,500.62 | 57,112 |
| 1 | gemini-omni-1.1-flash google | 1,488.49 | 1,477.57 – 1,499.41 | 3,734 |
| 1 | wan3.0 alibaba | 1,479.81 | 1,469.01 – 1,490.6 | 3,442 |
| 2 | dreamina-seedance-2.5-720p bytedance | 1,477.41 | 1,470.2 – 1,484.63 | 15,729 |
| 2 | dreamina-seedance-2.0-720p bytedance | 1,474.57 | 1,467.52 – 1,481.62 | 121,427 |
| 3 | gemini-omni-flash google | 1,464.83 | 1,459.29 – 1,470.37 | 87,155 |
| 6 | hidream-o1-video-1.0 hidream | 1,456.47 | 1,448.55 – 1,464.38 | 6,488 |
| 6 | grok-imagine-video-1.5-720p xai | 1,456.02 | 1,451.83 – 1,460.2 | 137,459 |
| 7 | flux-3-video-20260811 bfl | 1,449.45 | 1,444.5 – 1,454.39 | 37,042 |
| 8 | happyhorse-1.0 aorizon | 1,441.66 | 1,431.84 – 1,451.49 | 70,640 |
| 10 | wan2.7-i2v wan | 1,428.21 | 1,423.38 – 1,433.05 | 85,521 |
| 12 | grok-imagine-video-720p xai | 1,415.3 | 1,411.18 – 1,419.43 | 554,050 |
| 13 | veo-3.1-audio google | 1,398.1 | 1,387.6 – 1,408.59 | 25,116 |
| 13 | veo-3.1-audio-1080p google | 1,390.24 | 1,381.67 – 1,398.81 | 53,089 |
| 13 | veo-3.1-fast-audio google | 1,385.06 | 1,376.23 – 1,393.89 | 99,804 |
| 13 | grok-imagine-video-480p xai | 1,384.86 | 1,376.44 – 1,393.27 | 19,429 |
| 15 | veo-3.1-fast-audio-1080p google | 1,371.6 | 1,362.11 – 1,381.08 | 54,380 |
| 17 | vidu-q3-pro shengshu | 1,363.15 | 1,354.42 – 1,371.88 | 36,679 |
| 18 | kling-v3-pro kling | 1,354.01 | 1,348.5 – 1,359.53 | 206,221 |
| 20 | veo-3-audio google | 1,331.49 | 1,319.87 – 1,343.11 | 32,367 |
| 20 | veo-3-fast-audio google | 1,326.04 | 1,316.54 – 1,335.55 | 41,194 |
| 20 | wan2.5-i2v-preview alibaba | 1,321.38 | 1,311.07 – 1,331.68 | 16,907 |
| 22 | wan2.6-i2v alibaba | 1,309.54 | 1,302.76 – 1,316.31 | 121,082 |
| 22 | seedance-v1.5-pro bytedance | 1,307.2 | 1,300.06 – 1,314.33 | 245,206 |
| 23 | pixverse-v5.6 Organization not supplied | 1,299.26 | 1,291.95 – 1,306.56 | 126,710 |
| 24 | kling-2.6-pro kling | 1,293.95 | 1,286.18 – 1,301.73 | 202,113 |
| 26 | kling-2.5-turbo-1080p kling | 1,275.56 | 1,263.04 – 1,288.08 | 3,795 |
| 27 | seedance-v1-pro bytedance | 1,272.97 | 1,265.24 – 1,280.7 | 34,019 |
| 27 | hailuo-2.3 minimax | 1,261.97 | 1,257.07 – 1,266.88 | 405,786 |
| 27 | veo-3 google | 1,258.03 | 1,247.65 – 1,268.41 | 26,081 |
| 27 | veo-3-fast google | 1,257.44 | 1,247.63 – 1,267.26 | 26,272 |
| 29 | p-video Organization not supplied | 1,243.58 | 1,227.39 – 1,259.77 | 23,364 |
| 29 | vidu-q2-turbo shengshu | 1,243.55 | 1,226.82 – 1,260.29 | 2,509 |
| 32 | kling-v2.1-master kling | 1,235 | 1,227.13 – 1,242.86 | 29,824 |
| 32 | hailuo-02-pro minimax | 1,228.65 | 1,218.01 – 1,239.29 | 21,743 |
| 32 | kling-v2.1-standard kling | 1,228.63 | 1,220.3 – 1,236.97 | 29,957 |
| 32 | ray-3 luma-ai | 1,225.9 | 1,206.93 – 1,244.88 | 1,585 |
| 32 | hailuo-02-standard minimax | 1,223.71 | 1,214.16 – 1,233.26 | 21,785 |
| 32 | vidu-q2-pro shengshu | 1,223.36 | 1,206.62 – 1,240.09 | 2,614 |
| 38 | hunyuan-video-1.5 tencent | 1,197.77 | 1,182.12 – 1,213.43 | 5,462 |
| 40 | hailuo-02-fast minimax | 1,193.92 | 1,183.28 – 1,204.55 | 22,519 |
| 40 | seedance-v1-lite bytedance | 1,185.3 | 1,177.54 – 1,193.06 | 33,734 |
| 42 | wan-v2.2-a14b alibaba | 1,170.2 | 1,160.19 – 1,180.21 | 27,054 |
| 42 | veo-2 google | 1,165.79 | 1,149.63 – 1,181.95 | 10,303 |
| 43 | ltx-2-19b Organization not supplied | 1,159.35 | 1,154.48 – 1,164.22 | 262,336 |
| 46 | ray2 luma-ai | 1,108.47 | 1,092.24 – 1,124.71 | 9,521 |
| 47 | runway-gen4-turbo runway | 1,052.35 | 1,038.96 – 1,065.74 | 6,801 |
| 48 | pika-v2.2 pika | 997.07 | 983.4 – 1,010.74 | 8,635 |

## What this ranking can tell you

 - The population is the models in this source board, including variants and models without an available API price.
- Ranks use the published confidence bounds: one plus the number of models whose lower bound exceeds this model’s upper bound. Shared ranks are not proof of equal performance.

## Check the source

The original evidence is retained byte for byte. The downloadable board includes the source URLs, revision and SHA-256 hashes.

[Download this board and provenance →](/data/rankings/arena-image-to-video.json)

 Source files and licences - [metadata · a7a159f557a1](/data/rankings/evidence/a7a159f557a1e594a5d41218fe8d53c63c63daa39b655e51d6fc5b482a17d059.json) · [upstream source ↗](https://huggingface.co/api/datasets/lmarena-ai/leaderboard-dataset)
- [licence · 88a46d472f35](/data/rankings/evidence/88a46d472f35274fb6b7a852c3d16c8ee8007d51b37f290161537bec26895ee4.txt) · [upstream source ↗](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/raw/8b6deb69ace01ee8dcda9e46eba7a5e8a808ec53/README.md)
- [rows · 55fd7438208d](/data/rankings/evidence/55fd7438208d72ff4838978c4dc626060750918edda5c2a6f91fce193241090d.parquet) · [upstream source ↗](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/8b6deb69ace01ee8dcda9e46eba7a5e8a808ec53/image_to_video/latest-00000-of-00001.parquet)

[Explore other model types →](/rankings/)[Read the benchmark guide →](/benchmarks/)

## Continue your investigation

 - [Understand the measurements](/benchmarks/)
- [Compare task performance](/best/)
- [Compare embedding models](/embeddings/)
- [Inspect ranking rules](/methodology/)