Speech Agent Arena launches with Gemini leading human preference rankings

Artificial Analysis launched Speech Agent Arena, a blind human-preference leaderboard for speech-to-speech models tested on real tasks like ordering food. Gemini 3.1 Flash Live topped preference rankings while Grok led in task success rate.

2026-08-21 ~ 2026-08-22 · 3 related posts

• Speech Agent Arena Launch: Gemini Leads Preference, Grok Leads Success Rate — ArtificialAnlys · 2026-08-21
• Speech-to-Speech Model Analysis: Grok Leads Task Success, Gemini Top Preference — ArtificialAnlys · 2026-08-21
• Gemini 3.1 Flash Live tops new Speech Agent Arena; GPT-Realtime-1.5 leads task success — _philschmid · 2026-08-22