加载中...
加载中...
基于 Text-to-Video Arena 用户匿名投票的最新AI视频生成模型排行榜，涵盖各模型的 Elo 得分、95% 置信区间、投票量、机构与许可证。
Top Model
veo-3.1-audio
Top Score
1,371
Model Count
31
Data version
2026年01月29日
Data source: LM Arena
This leaderboard ranks AI text-to-video models by generation quality. Data comes from LMArena's Text-to-Video Arena track, evaluated through anonymous blind testing by real users.
Blind testing: Users submit text descriptions, two anonymous models generate videos, and users vote for the better result.
Elo scoring: Based on the Bradley-Terry model. Higher scores indicate stronger user preference for that model's video output.
Chart Source: DataLearnerAI · Data Source: LMArena
| Rank | Model | Score | 95% CI | Votes | Organization | License |
|---|---|---|---|---|---|---|
| 1 | veo-3.1-audio | 1,371 | +14 | 12,572 | Proprietary | |
| 2 | sora-2-pro | 1,369 | +11 | 11,435 | OpenAI | Proprietary |
| 3 |
Data is for reference only. Official sources are authoritative. Click model names to view DataLearner model profiles.
Google 的 veo-3.1-audio 登顶榜首 (1371)，OpenAI 的 sora-2-pro 紧随其后 (1369)。
grok-imagine-video 表现惊艳，排名第四。wan2.5-12v-preview 领跑国产模型，排名第八 (1267)。veo-3.1-audio
Elo 1371, SOTA, Google
sora-2-pro
Elo 1369, OpenAI Top Model
wan2.5-12v-preview
Elo 1267, Alibaba, Top Domestic
seedance-v1.5-pro
Elo 1261, Bytedance
目前 veo-3.1-audio 和 sora-2-pro 并驾齐驱，代表了行业最高水平。
Wan2.5 (阿里)、Seedance (字节)、Kling (快手)、Hailuo (MiniMax) 依然是第一梯队。
Diverse generation scenarios: Covers natural landscapes, human motion, creative animation, product showcases, and more.
DataLearner provides in-depth analysis on top of the raw data, linking leaderboard models to the DataLearner model database so you can quickly access model details, API pricing, benchmark scores, and more.
| 1,367 |
| +13 |
| 13,963 |
| Proprietary |
| 4 | grok-imagine-video | 1,362 | +13 | 7,952 | xAI | Proprietary |
| 5 | veo-3-fast-audio | 1,350 | +11 | 25,771 | Proprietary |
| 6 | veo-3-audio | 1,340 | +12 | 19,309 | Proprietary |
| 7 | sora-2 | 1,338 | +10 | 14,207 | OpenAI | Proprietary |
| 8 | wan2.5-12v-preview | 1,267 | +17 | 6,077 | Alibaba | Proprietary |
| 9 | seedance-v1.5-pro | 1,261 | +10 | 13,960 | Bytedance | Proprietary |
| 10 | veo-3 | 1,257 | +11 | 15,192 | Proprietary |
| 11 | veo-3-fast | 1,251 | +12 | 15,476 | Proprietary |
| 12 | kling-2.5-turbo-1080p | 1,222 | +17 | 2,054 | KlingAI | Proprietary |
| 13 | kling-2.6-pro | 1,219 | +9 | 17,486 | KlingAI | Proprietary |
| 14 | kling-o1-pro | 1,207 | +27 | 1,197 | KlingAI | Proprietary |
| 15 | ray-3 | 1,204 | +23 | 1,057 | Luma AI | Proprietary |
| 16 | hailuo-02-pro | 1,200 | +12 | 9,888 | MiniMax | Proprietary |
| 17 | hailuo-2.3 | 1,198 | +10 | 13,037 | MiniMax | Proprietary |
| 18 | seedance-v1-pro | 1,192 | +11 | 12,895 | Bytedance | Proprietary |
| 19 | hailuo-02-standard | 1,181 | +11 | 9,935 | MiniMax | Proprietary |
| 20 | kandinsky-5.0-12v-pro | 1,178 | +21 | 1,888 | Kandinsky | MIT |
| 21 | hunyuan-video-1.5 | 1,171 | +16 | 4,301 | Tencent | tencent-hun... |
| 22 | kling-v2.1-master | 1,168 | +9 | 14,527 | KlingAI | Proprietary |
| 23 | veo-2 | 1,165 | +16 | 7,106 | Proprietary |
| 24 | wan-v2.2-a14b | 1,130 | +15 | 11,160 | Alibaba | Apache 2.0 |
| 25 | seedance-v1-lite | 1,114 | +9 | 16,716 | Bytedance | Proprietary |
| 26 | kandinsky-5.0-12v-lite | 1,112 | +18 | 1,351 | Kandinsky | MIT |
| 27 | ltx-2-19b | 1,090 | +13 | 8,759 | lightricks | ltx-2-comm... |
| 28 | sora | 1,070 | +14 | 4,521 | OpenAI | Proprietary |
| 29 | ray2 | 1,066 | +17 | 5,611 | Luma AI | Proprietary |
| 30 | pika-v2.2 | 1,011 | +15 | 6,496 | Pika | Proprietary |
| 31 | mochi-v1 | 999 | +16 | 6,661 | Genmo AI | Apache 2.0 |