DrugBench
Explore score history ↗DrugBench evaluates AI control protocols for mitigating medication-related harm using 3,671 medical conversations and FDA drug labels, covering drug interactions, contraindications, dosing constraints, and patient action restrictions. Introduces severity-based monitoring.
- Released
- 2026-06-10
- Institutions
- Universidad de Buenos Aires
- Evaluates
- Biology & Drug Discovery, General AI, Language & Knowledge, cs.AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
DrugBench paper
No reported scores are on record for this benchmark yet.