---
title: "Text to video leaderboard"
description: "Rankings of text-to-video models."
canonical: https://pirouter.ai/rankings/t2v
last-updated: 2026-10-15
---

# Text to video leaderboard

> Rankings of text-to-video models.

- Updated: 2026-09-22
- 1,235,424 votes · 48 models
- Score · higher is better

## Full ranking

| Rank | Rank spread | Model | Vendor | Score | Votes |
|---|---|---|---|---|---|
| 1 | 1–4 | Gemini Omni 1.1 Flash | Google | 1516 ±15 | 1784 |
| 2 | 1–4 | Gemini Omni Flash | Google | 1513 ±9 | 26576 |
| 3 | 1–7 | Flux 3 Video | Black Forest Labs | 1493 ±17 | 1302 |
| 4 | 1–7 | Grok Imagine Video 1.5 Agent | xAI | 1492 ±18 | 1218 |
| 5 | 3–7 | Dreamina Seedance 2.0 720p | ByteDance | 1479 ±8 | 56318 |
| 6 | 3–9 | Wan3.0 | Alibaba | 1476 ±13 | 2598 |
| 7 | 3–9 | Dreamina Seedance 2.5 720p | ByteDance | 1474 ±9 | 8001 |
| 8 | 6–9 | Minimax H3 | MiniMax | 1460 ±9 | 11417 |
| 9 | 6–9 | Muse Video | Meta | 1456 ±15 | 2188 |
| 10 | 10–10 | Happyhorse 1.0 | Aorizon | 1427 ±13 | 22264 |
| 11 | 11–15 | Sora 2 Pro | OpenAI | 1368 ±7 | 54167 |
| 12 | 11–17 | Veo 3.1 Audio | Google | 1364 ±14 | 13741 |
| 13 | 11–17 | Veo 3.1 Audio 1080p | Google | 1362 ±10 | 25076 |
| 14 | 11–17 | Veo 3.1 Fast Audio | Google | 1362 ±10 | 39484 |
| 15 | 11–19 | Veo 3.1 Fast Audio 1080p | Google | 1358 ±10 | 25870 |
| 16 | 12–20 | Veo 3 Fast Audio | Google | 1348 ±11 | 25258 |
| 17 | 15–20 | Sora 2 | OpenAI | 1343 ±6 | 71947 |
| 18 | 15–20 | Grok Imagine Video 720p | xAI | 1342 ±6 | 165462 |
| 19 | 12–21 | Veo 3 Audio | Google | 1340 ±13 | 19002 |
| 20 | 16–21 | Wan2.7 T2v | Wan | 1337 ±7 | 27626 |
| 21 | 19–21 | Wan2.6 T2v | Alibaba | 1327 ±7 | 54050 |
| 22 | 22–26 | Seedance V1.5 Pro | ByteDance | 1256 ±7 | 76171 |
| 23 | 22–26 | Veo 3 | Google | 1254 ±11 | 15005 |
| 24 | 22–27 | Veo 3 Fast | Google | 1248 ±12 | 15283 |
| 25 | 22–27 | Wan2.5 T2v Preview | Alibaba | 1245 ±9 | 36378 |
| 26 | 22–29 | Pixverse V5.6 | — | 1240 ±11 | 32434 |
| 27 | 26–32 | Runway Gen 4.5 | Runway | 1225 ±9 | 48127 |
| 28 | 24–34 | Kling 2.5 Turbo 1080p | Kling | 1220 ±17 | 2111 |
| 29 | 27–34 | Kling 2.6 Pro | Kling | 1216 ±7 | 73362 |
| 30 | 27–37 | P Video | — | 1207 ±16 | 7079 |
| 31 | 27–38 | Ray 3 | Luma | 1206 ±22 | 1136 |
| 32 | 28–35 | Hailuo 2.3 | MiniMax | 1206 ±6 | 89138 |
| 33 | 26–39 | Kling O1 Pro | Kling | 1205 ±27 | 1194 |
| 34 | 28–37 | Hailuo 02 Pro | MiniMax | 1199 ±13 | 9399 |
| 35 | 30–39 | Seedance V1 Pro | ByteDance | 1191 ±11 | 12164 |
| 36 | 31–40 | Hailuo 02 Standard | MiniMax | 1181 ±12 | 9379 |
| 37 | 31–41 | Kandinsky 5.0 T2v Pro | Kandinsky | 1175 ±21 | 2019 |
| 38 | 33–41 | Hunyuan Video 1.5 | Tencent | 1169 ±16 | 4292 |
| 39 | 34–41 | Veo 2 | Google | 1164 ±16 | 6531 |
| 40 | 36–41 | Kling V2.1 Master | Kling | 1163 ±10 | 14104 |
| 41 | 37–42 | Ltx 2 19b | — | 1154 ±8 | 75596 |
| 42 | 41–44 | Wan V2.2 A14b | Alibaba | 1132 ±15 | 10458 |
| 43 | 42–44 | Seedance V1 Lite | ByteDance | 1113 ±10 | 16253 |
| 44 | 42–44 | Kandinsky 5.0 T2v Lite | Kandinsky | 1113 ±18 | 1474 |
| 45 | 45–46 | Sora | OpenAI | 1069 ±16 | 4082 |
| 46 | 45–46 | Ray2 | Luma | 1065 ±17 | 5250 |
| 47 | 47–48 | Pika V2.2 | Pika | 1009 ±15 | 5763 |
| 48 | 47–48 | Mochi V1 | Genmo | 1007 ±17 | 5893 |

## FAQ

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

As of 2026-09-22, Google Gemini Omni 1.1 Flash is #1 on the text to video board with a score of 1516, rank spread 1–4.

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

Minimax H3 (MiniMax), #8 on this board.

### What does this board rank?

Rankings of text-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/text-to-video