Phonic 1 Tops Artificial Analysis Speech-to-Speech Index at 87.1, Edging Grok Voice 3.0
ArtificialAnlys · x · 2026-10-30
Artificial Analysis' Speech to Speech Index has a new leader: Phonic 1 (High) debuts at #1 of 22 with 87.1, narrowly beating Grok Voice 3.0 (86.9).
- Agentic performance: #1 on Tau Voice at 79.9%, a 5.4-point lead over GPT-Live-1 (Astra, medium) — the benchmark tests policy-following and multi-step tool use in long customer-service tasks
- Speech reasoning: 98.9% on Big Bench Audio, #3 behind StepAudio 3 Realtime (99.7%) and Qwen Audio 3.0 Realtime Plus (99.2%)
- Arena: Elo 1012 (#8 of 30) in blind live-voice preference, with a 92.3% task success rate (#4)
- Speed: 0.61s time-to-first-audio, fastest among the top 5 and 25% quicker than Grok Voice 3.0
- Cost: $0.07/min ($4.20/hour of input audio), below Grok Voice 3.0 ($4.80) and roughly 2.6x cheaper than GPT-Realtime-2.1 High ($10.75)
Related event: Phonic 1 Tops Artificial Analysis Speech-to-Speech Index at 87.1(8 posts)→
More from Models
- One neuron, one persona: 12,288 params turn Qwen3-8B into Hoot the owl — maxsloef · 2026-10-30
- Dream raises $17M seed from a16z to build spatial-reasoning AI for AEC — a16z · 2026-10-30
- Investor bets speech-to-speech will be massive, praises Phonic's model — graceisford · 2026-10-30
- User Praises OpenAI for Doubling Pro Usage and Including API in Pro Sub — Angaisb_ · 2026-10-30
- OpenAI doubles usage limits for Pro tiers and Business Premium, effective immediately — Polymarket · 2026-10-30
- Gemini 4 Argon tops 4 robotics tasks on RLE-Bench, ranks #2 behind GPT-6 Astra — daibond_alpha · 2026-10-30