GPT-Live-1 leads Tau Voice at 67.9% but trails Grok on audio reasoning
ArtificialAnlys · x · 2026-09-15
GPT-Live-1 (Astra, medium) leads the Tau Voice agentic benchmark at 67.9%, ahead of (Sol, low) at 59.3% and Grok at 56.5% — the main driver of its overall Index lead. On Big Bench Audio reasoning it scores 90.1%/89.0%, behind Grok's 97.2%. On the Full Duplex Bench subset it scores 94.9%/97.3%. Both configs are currently based on a single trial.
Related event: OpenAI's GPT-Live-1 Tops Artificial Analysis Speech-to-Speech Index at 81.5(6 posts)→
More from Models
- ICML paper: finite context windows impose impossibility results for adversarial regret — burny_tech · 2026-11-02
- SenseTime open-sources SenseNova-Loop-9B: weight-shared 56-layer loop, 256K context, Apache 2.0 — AdinaYakup · 2026-11-02
- User says Gemini excels at long-form fanfic, producing stories up to 29 minutes of reading — Ok-Jello3739 · 2026-11-02
- Sam Altman calls tokens 'a kind of fake unit' that doesn't measure business value — rohanpaul_ai · 2026-11-02
- 'You Can Feel the Gradient Slopes': Dev Contrasts Benchmaxxed RL Models vs General Ones — theteknosaur · 2026-11-02
- LightOnOCR-3 Launches: Tops FRBench, Adds Layout Structure and Chart Extraction — IgorCarron · 2026-11-02