Phonic 1 (High) ranks first on Tau Voice at 79.9%, debuts #8 in Speech Agent Arena

AIPhonic 1 (High) debuts at #8 of 30 in Artificial Analysis's Speech Agent Arena, where blind live voice conversations pick the preferred model, with an Elo of 1012. It ranks behind Cartesia Managed Agents, Gemini 3.1 Flash Live Minimal and Gemini 3.8 Live, and ahead of Eleven Realtime v1 Max. It completes 92.3% of tasks successfully, placing #4 on Task Success Rate behind Grok Voice 3.0, Grok Voice 2.0 and Gemini 3.8 Live.

AIArtificial Analysis says Phonic 1 (High) ranks first on Tau Voice with 79.9%, 5.4 points ahead of GPT-Live-1 (Astra, medium) at 74.5%. Grok Voice 3.0 scored 71.6%, Gemini 3.8 Live Extended Thinking (High) 68.6%, and GPT-Live-1 (Sol, low) 59.3%. The benchmark tests strict policy-following and multi-step tool use in long customer-service tasks, unlike the shorter live conversations in its Arena.