GPT-Live-1 Speech Agent Evaluated: Strong Preference Ranking, Trails Grok in Audio Reasoning

Artificial Analysis's Speech Agent Arena shows GPT-Live-1 ranking 3rd–4th in preference with 1,053 Elo and a leading 90.9% task success rate, though its audio reasoning still trails Grok.

2026-09-15 ~ 2026-09-15 · 2 related posts