ClinEnv Benchmark
Explore score history ↗ClinEnv evaluates LLMs as physicians in an interactive multi-stage EHR simulation, requiring queries to four specialized agents before committing to medical decisions, scored via ontology-grounded matching.
- Released
- 2026-06-01
- Institutions
- Georgia Institute of Technology · Peking University · The University of Texas Southwestern Medical Center
- Evaluates
- Agents & Tool Use, Biology & Drug Discovery, cs.AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
ClinEnv paper
No reported scores are on record for this benchmark yet.