xAI launches Grok Voice 3.0, tops Artificial Analysis speech index at 86.9
rohanpaul_ai · x · 2026-10-15
xAI released Grok Voice 3.0, a speech-to-speech model that tops Artificial Analysis's Speech-to-Speech Index at 86.9, beating GPT-Live-1 Astra (83.2) and Gemini 3.8 Live (82.6). It scores 71.6% on τ-Voice customer-support tasks at 40% lower latency than GPT-Live-1, hits 97% on Full Duplex Bench for natural turn-taking, achieves 94.8% task success and an Elo of 1070, and ships in the API at the same price as its predecessor with sub-second latency. It already powers millions of daily conversations across Tesla and SpaceX.
Related event: xAI launches Grok Voice 3.0, tops Speech-to-Speech Index(16 posts)→
More from Models
- Dev says Gemini 4 is 'outright unusable' for real code work due to hallucinations — gnukeith · 2026-10-15
- Scale CEO spotlights Muse Wonder: untrained for 3D yet beats Gemini 4 in physics visualization tests — alexandr_wang · 2026-10-15
- Cohere tops WMT26 translation benchmark: small agentic model scores 84.36, beating Mistral and DeepL — cohere · 2026-10-15
- Anthropic has never launched a Sonnet/Opus-tier model on a Wednesday — ChrisGPT · 2026-10-15
- 8k context beats 480k: OpenAI Decisions API cuts costs 84% at 98.25% F1 — OpenAIDevs · 2026-10-15
- Gemini 4 Argon hit with HTTP 524 timeouts outside Antigravity; Google payment also glitching — cedric_chee · 2026-10-15