RCM-Bench-1
Health & Medicine · 2026-10-02
Commure's benchmark of AI agents on healthcare revenue cycle work: 97 scenarios across six workflows, run three times each through Commure's RCM agent harness with mocked tools or isolated backends. Checks cover tool calls, arguments, response content and resulting state. The score is the equal-weight mean of the six workflow pass rates, with failures kept in the denominator. Cases and transcripts are private, and Commure says scores describe the agent configuration rather than standalone model quality.
Benchmark source: Commure