ModelsMulti-source

Tavus发布Griffin视频模型

Why we picked it

Tavus的Griffin模型在视频对话领域取得突破性进展,通过率高达48%,远超之前的系统。

Tavus推出Griffin模型,成为首个通过图灵测试的视频模型。48%的测试者认为与它实时对话是在与真人交流,远超之前系统不到3%的通过率。

Body

该模型在NVIDIA全双工AI视频基准测试中排名第一,也是首个人交互模型(HIM)。

Original · Replicate

Thrilled to be powering Griffin from @tavus on Replicate! Tavus @tavus Introducing Griffin, the first model to pass the video Turing test. 48% of people who talked to it live thought it was a real human. Previous systems have had a pass rate <3%. It is #1 on NVIDIA's benchmark for full-duplex AI video. It’s the first Human Interaction Model (HIM).

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Models" desk. Key entities and technical topics under continuous tracking include Griffin, Tavus, video generation, Turing test.

Source attribution: curated from Replicate (@replicate). Cross-source corroboration: 9 independent sources have covered this development (including TestingCatalog, shao__meng, rohanpaul_ai), confirming industry-wide signal strength.