Got early access to Tavus Griffin.
I went in expecting another impressive AI demo. Instead, I found myself reacting to it like I was on an actual video call.
The way it notices, responds and jumps into the conversation is something you have to experience to appreciate.
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).
Community note
The 48% figure and "video Turing test" claim are from Tavus's own study of 54 one-minute calls, not independently verified or using a standard protocol. Griffin-Lite leads NVIDIA's VideoFDB benchmark on their public leaderboard.
cellcog.ai/blog/tavus-gri…
research.nvidia.com/labs/amri/proj…
tech-ish.com/2026/10/02/tav…
Oct 1, 2026 · 6:32 PM UTC
35
32
94
52,074
