From the source
Cartesia is launching Managed Agents, an end-to-end voice agent platform for enterprise conversations, which it says ranks first on independent voice agent benchmarks at launch.
- The company says it co-designed its voice models and the harness as one system so listening, turn-taking, reasoning, tool-calling and speech are tuned together, rather than relying on cascaded pipelines or hard-to-control speech-to-speech models.
- On Artificial Analysis's Speech Agent Arena, where blind human raters compare agents on tasks such as booking appointments and ordering takeout, Managed Agents ranks first of 30 agents with a preference Elo of 1115, with benchmarks run using GPT-5.5 as the reasoning model.
- On EVA-Bench, ServiceNow's open benchmark for enterprise voice agents in CSM, ITSM and HR, Cartesia reports the highest scores for both accuracy (87%) and experience (91%) across more than 200 scenarios.
- In internal evaluations, callers reported no turn-taking issues in 85% of conversations with Managed Agents, compared with 67% for other agents.
- The platform bundles telephony, knowledge bases and tool integrations, supports agents in 44 languages with mid-conversation switching between English, Spanish, Hindi, French and Japanese, and offers outbound batches for scheduling thousands of personalized calls.
- Cartesia says Managed Agents has already powered tens of millions of conversations in finance, retail, hospitality and healthcare.
