ALL INTELLIGENCE
Artificial Analysis (@ArtificialAnlys)T1·Agents

Cartesia Voice Agents Score Higher in Arena Benchmark

Original title: Cartesia Managed Agents scores an Elo of 1115 on the Artificial Analysis Speech Agent Arena, 98 poin...
45AI Score

Cartesia Managed Agents achieved an Elo score of 1115 on the Artificial Analysis Speech Agent Arena, a 98-point improvement over its predecessor. Task success rates rose from 77.5% to 91.7%, driven by a cascaded architecture combining Ink STT/TTS models with GPT-5.5.

Full Report

Artificial Analysis (@ArtificialAnlys) · 2026-10-27 22

Cartesia Managed Agents scores an Elo of 1115 on the Artificial Analysis Speech Agent Arena, 98 points above Cartesia's earlier voice agent product, Cartesia Line, with Task Success Rate up from 77.5% to 91.7%

Managed Agents is @CartesiaAI's fully managed platform for building and deploying voice agents. It is a cascaded system: Cartesia's own Ink Speech to Text and Sonic Text to Speech models run around an LLM of the developer's choice. We evaluated Cartesia Managed Agents with GPT-5.5 as the LLM and the Skylar and Daniel voices.

Key takeaways:

➤ Speech Agent Arena: Cartesia Managed Agents scores an Elo of 1115 (95% CI 1086-1144, 685 samples), 98 points above Cartesia Line at 1017 (95% CI 985-1049)

➤ Agentic tasks: On tasks that need tool calls, Cartesia Managed Agents scores an Elo of 1112

➤ Task Success Rate: 91.7% of eligible tool-calling conversations end with the correct final task-completing tool call

Congrats to the @CartesiaAI team!

See below for more details ⬇️

推文配图