Benchmark RadarPhysAssistBench
PhysAssistBench evaluates interactive doctor-patient-EHR assistance. It contains 1,296 physician-validated turns from MIMIC-IV cases, testing coordination of clinical knowledge, patient communication, and EHR tool use.
- Released
- 2026-06-17
- Readiness
- Paper only
- Primary field
- Health & Life Sciences
Why it matters
Current medical LLM evaluations isolate capabilities, but real physician assistance requires integrating knowledge, communication, and systems. PhysAssistBench provides a realistic interaction setting to assess readiness for clinical deployment.
Motivation
The most plausible near-term role of medical LLMs is to assist rather than replace physicians, yet current evaluations often test isolated capabilities: clinical knowledge, EHR system interaction, or patient communication.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.