VQV Signal
According to a post on X by @TrelisResearch, the group ran voice models from OpenAI, Google, ElevenLabs and Phonic through a 60-second quiz. The models answered nearly every question correctly but differed in verbosity and response speed. Google's Gemini 3.8 Live finished first, ahead of OpenAI's 1.0 Live and ElevenLabs Realtime Mini.
According to a post on X by @TrelisResearch, the group ran voice models from OpenAI, Google, ElevenLabs and Phonic through a 60-second quiz. The models answered nearly every question correctly but differed in verbosity and response speed. Google's Gemini 3.8 Live finished first, ahead of OpenAI's 1.0 Live and ElevenLabs Realtime Mini.
AI-assisted summary based on the listed source.
Trelis ran OpenAI, Google, ElevenLabs and Phonic voice models through a 60-second quiz where all answer nearly every question correctly but differ in verbosity and response speed. Google's 3.8 Live won, ahead of OpenAI's 1.0 Live and ElevenLabs Realtime Mini. Why it matters: For voice agents, speed and brevity...
The post argues that for voice agents, speed and brevity matter as much as accuracy, and that this benchmark captures those differences. Teams comparing real-time voice models may want to weigh response speed and answer length alongside correctness. This is a single social post describing one short quiz, so readers should check the full methodology before relying on the ranking.
VQV organizes public signals from inspectable sources. It does not independently verify the underlying report.
Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.
VQV surfaced this signal because it is recent, relevant to AI Voice, connected to Scobleizer News Pulse (X).
No login, cookies, social SDKs, or automatic posting.
