Introducing HealthBench
OpenAI releases HealthBench, a new healthcare AI benchmark built with 250+ physicians covering realistic clinical scenarios, establishing a shared safety and performance standard.
Excerpt
HealthBench is a new evaluation benchmark for AI in healthcare which evaluates models in realistic scenarios. Built with input from 250+ physicians, it aims to provide a shared standard for model performance and safety in health.
Read at source: https://openai.com/index/healthbench