MedFailBench: A Clinician-Built Open-Source Benchmark for Medical AI Safety Boundary Inspection
The authors present MedFailBench, a synthetic medical AI benchmark that labels errors by severity and safety gate type.
MedFailBench is novel as it focuses on identifying which safety boundary failed instead of just whether the model is correct.
Before reading this…
Applications
- →Medical AI research and development
To understand this paper, make sure you know these concepts first:
- Understanding of medical AI and benchmarking conceptsfind papers →
Abstract
More Like ThisMost medical AI benchmarks measure whether a model knows the correct answer. MedFailBench asks a different question: which safety boundary failed? We present a clinician-built synthetic benchmark and failure atlas that labels medical AI errors by severity (1--5) and safety gate type (missed urgent escalation, unsafe remote dosing, unsafe discharge reassurance, evidence fabrication, unsafe protocol execution, source support gap). The current public release (v0.2.1) contains 44 clinician-reviewed synthetic cases with severity annotations, a live HuggingFace leaderboard preview, a safety gate taxonomy, a clinical severity rubric, and an automated pipeline for archiving model-response screening runs. No patient data, clinical validation claims, or model rankings are included. MedFailBench is released under Apache-2.0 and CC-BY-4.0 and carries the Zenodo DOI 10.5281/zenodo.21205535.