--- format: "aidr-story-markdown/v1" id: "dd0835ebdf20cf0bc2b15469a2789189c017790ba8b564a1412475867fbeb4f5" canonical_url: "https://aidr.today/dd0835eb?lang=en" title: "Tavus AI Fools 48% of Humans in First Video Turing Test Pass" lang: "en" requested_lang: "en" available_langs: ["en","vi"] translation_fallback: null fallback_fields: [] published_at: "2026-10-01T17:40:41.000Z" category: "Agents" topics: ["agent"] source_urls: ["https://marketbrief.now/ai/tavus-ai-fools-48percent-of-humans-in-first-video-turing-test-pass-170f5fb1","https://huggingnews.com/ai/tavus-ai-fools-48percent-of-humans-in-first-video-turing-test-pass-170f5fb1"] summary: "Tavus's Griffin model, a Human Interaction Model, allows users to have face-to-face conversations with a synthetic agent that can see and hear simultaneously. In a company study, 48% of participants believed they were speaking with a real person, and the model scored 3.83 out of 5 on Nvidia's VideoFDB benchmark. Tavus is currently limiting access to a Griffin-Lite version for trusted testers while implementing safety and disclosure measures." --- # Tavus AI Fools 48% of Humans in First Video Turing Test Pass > [Open the canonical story]() **Published:** 2026-10-01T17:40:41.000Z **Category:** Agents **Topics:** agent ## Summary Tavus's Griffin model, a Human Interaction Model, allows users to have face\-to\-face conversations with a synthetic agent that can see and hear simultaneously\. In a company study, 48% of participants believed they were speaking with a real person, and the model scored 3\.83 out of 5 on Nvidia's VideoFDB benchmark\. Tavus is currently limiting access to a Griffin\-Lite version for trusted testers while implementing safety and disclosure measures\. ## Sources - [Story source]() - [Story source]()