Benchmark RadarDOSEBENCH
DOSEBENCH evaluates LLM decision-making on over-the-counter dosing questions, with 81 curated scenarios for adult acetaminophen and ibuprofen use. Correct answers require tracking dose timing, computing rolling 24-hour intake, and following product-label constraints.
- Released
- 2026-06-02
- Readiness
- Paper only
- Primary field
- Health & Life Sciences
Why it matters
Addresses an underexplored safety-relevant medical QA setting. Evaluates temporal reasoning, constraint following, and uncertainty handling, showing that confident responses can violate dosing constraints.
Motivation
Large language models (LLMs) are increasingly used for everyday health questions, including whether a user can safely take another dose of an over-the-counter (OTC) medication.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.