Unverified50% confidenceReleaseExact time
HealthBench is a public evaluation benchmark released by OpenAI in May 2025, comprising roughly 5,000 multi-turn conversational evaluation items written by practicing physicians from multiple countries, each paired with physician scoring criteria.
1
Sources
50%
Confidence
Long-term
Relevance
10/25/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn HealthBench, doctors first wrote the grading rubric, and OpenAI's GPT-4.1 evaluator exceeded the average doctor's level on 5 of 7 topics.71% similarUnverifiedThe study evaluates on the MedCalc-Bench Verified benchmark, which contains 1,100 cases covering 55 calculators.62% similarUnverifiedWhen a health threshold is breached, OpenRig issues a health warning and notifies the author via Slack, while also notifying a designated agent with relevant work context to handle the analysis61% similarUnverified团队构建了包含约4400个病例、覆盖20个专科的动态临床评估数据集MedIQ-Bench58% similarUnverifiedHealth benchmarks usually refer to evaluating a model's level of medical knowledge using standardized medical question-answering datasets (such as MedQA, PubMedQA, etc.), with accuracy as the main metric; such tests assume by default that the model should try to give an answer, but Tabibu's safety layer actively refuses diagnosis and so on, causing many questions it could have answered correctly to be intercepted by safety fallbacks.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1096540API
curl https://kongchang.com/api/v1/knowledge/claims/1096540MCP
get_claim(id=1096540)