Speech Arena: GPT-Live-1 ranks #3-4, Grok leads task success at 94.6%

ArtificialAnlys · x · 2026-09-15

On the Artificial Analysis Speech Agent Arena, GPT-Live-1 (Sol, low) ranks #3 in preference at 1,053 Elo with 90.9% task success; (Astra, medium) is #4 at 1,048 Elo with 87.4%. Gemini 3.1 Flash Live Minimal leads preference (1,096 Elo) but only 74.6% task success; Grok Voice Think Fast 2.0 High leads task success at 94.6% (1,011 Elo). Confidence intervals of the two GPT-Live-1 configs overlap.

Related event: GPT-Live-1 Speech Agent Evaluated: Strong Preference Ranking, Trails Grok in Audio Reasoning(2 posts)→

Original post →

More from Models

Models channel →