Name: 文生视频模型排行榜（开源模型2026-07-05排行榜）最好的 AI 视频生成器 |AITNT
Creator: LM Arena
License: https://creativecommons.org/licenses/by/4.0/
Keywords: 开源模型,AI 文生视频模型排行榜,文生视频排行榜,最佳 AI 视频生成器,AI 模型排行

文生视频模型 Arena 榜单LM Arena Global AI Leaderboard开源模型🔓Open Source

比较并探索基于开源模型场景进行 Elo 积分排名的主流文生视频 AI 模型，数据来源于真实用户匿名盲测。Explore Elo rankings of text-to-video AI models — quality judged by real anonymous user blind tests.

2026-07-05

▾

上榜模型Models

参赛厂商Providers

77.9K

总投票数Total Votes

📖 指标说明 — 读懂这张榜单📖 Metrics Guide — Understanding the Leaderboard

🎯

榜单主指标（Score）Primary Metric (Score)

每个榜单会采用官网对应的核心排序指标。通用 Arena 榜单通常是模型竞技积分；智能体榜单则展示净提升及多项任务指标。

Each leaderboard uses the official primary ranking metric. Most Arena boards use competitive scores; the Agent board uses net improvement and task-specific metrics.

🔢

精确值（Float Value）Float Value

主指标的完整浮点数值。对于通用 Arena 榜单可用于区分整数分相近的模型；智能体榜单以百分比和置信区间展示。

The full floating-point value of the primary metric. It helps distinguish close scores on standard boards; Agent metrics are shown as percentages with confidence intervals.

📊

方差（Variance）Variance

衡量结果的统计稳定程度。绿色·稳定（<5）更可信；橙色·波动（5~12）；红色·不稳（>12）说明排名还可能明显变化。

Measures statistical stability. Green·Stable (<5); Orange·Unstable (5–12); Red·Volatile (>12) means the ranking may still move significantly.

↔️

置信区间（95% CI = ±N）95% Confidence Interval (CI = ±N)

95% 置信区间反映当前估计的不确定范围，显示为 ±N。在相同计算口径下，N 越小说明估计越集中、排名越稳定。

The 95% confidence interval, shown as ±N, summarizes uncertainty in the current estimate. Under the same methodology, a smaller N indicates a more precise estimate and a more stable ranking.

🗳️

投票数（Vote Count）Vote Count

该模型或厂商参与评测的总次数。数量越高，结果的统计置信度越高、越不容易受单次样本影响而波动。

Total evaluation volume for the model or lab. Higher counts mean higher statistical confidence and less sensitivity to individual samples.

📜

开源协议（License）License

Apache/Llama：完全开源可商用；MIT：开源限制极少；Proprietary：闭源商业模型。协议决定你能否把它集成到自己的产品里。

Apache/Llama: Fully open-source, commercial use allowed; MIT: Open-source, minimal restrictions; Proprietary: Closed-source commercial model. License determines if you can integrate it into your product.

排名Rank	名次区间Rank Range	模型Model		投票数Votes	精确分 & 区间Float Score & CI	方差Variance	价格 ($/1M)Price ($/1M)	上下文Context
🥇	24 - 35	kandinsky-5.0-t2v-pro Kandinsky · MIT	1172±20.0	2.0K 票votes	1172.000 [1152.0, 1192.0]	11.00 · 波动Unstable	—	—
🥈	26 - 35	hunyuan-video-1.5 腾讯 · tencent-hunyuan-community	1169±16.0	4.3K 票votes	1169.000 [1153.0, 1185.0]	9.00 · 波动Unstable	—	—
🥉	31 - 36	ltx-2-19b · ltx-2-community-license-agreement	1143±10.0	53.9K 票votes	1143.000 [1133.0, 1153.0]	5.00 · 波动Unstable	—	—
4	35 - 38	wan-v2.2-a14b 阿里巴巴 · Apache 2.0	1131±15.0	10.4K 票votes	1131.000 [1116.0, 1146.0]	3.00 · 稳定Stable	—	—
5	36 - 38	kandinsky-5.0-t2v-lite Kandinsky · MIT	1113±18.0	1.5K 票votes	1113.000 [1095.0, 1131.0]	2.00 · 稳定Stable	—	—
6	41 - 42	mochi-v1 Genmo AI · Apache 2.0	1005±16.0	5.9K 票votes	1005.000 [989.0, 1021.0]	1.00 · 稳定Stable	—	—

🔍

没有找到匹配的模型，换个关键词试试？No matching models found. Try a different keyword?