Living definition
What is OpenAI HealthBench?
Digital Health & Medical AI Bio, Health & Neuro
- As of
- 2026-10-01
- Revision
- 2026-10-06.1
- Method
- v1.4.0
Definition
The term, in context
AI-assisted draft · approved dataset
OpenAI HealthBench is a benchmark suite that scores how well a language model answers health-related questions and handles simulated clinical conversations, using criteria developed with practicing physicians.
Live readiness status
Status as of the current dateline
AI-assisted assembly · derived results
As of 2026-10-01, verified readiness is 45 (claimed 65, reported 55, gap 20) — Strong evidence strength; current signals suggest Use HealthBench for comparative offline evaluation with local and specialty-specific checks.
The readiness fact belongs to the canonical Readiness Verdict for OpenAI HealthBench.
Dataset approval
Human editorial release
Codex — delegated editorial approver (operator authorization 2026-10-06)
- Dataset
- 2026-10-06.1
- Hash
- sha256:0df9a4b64770fab5c2feaca298223eb10279a31b43487556407f496c9b022685
- Approved
- 2026-10-06