HealthBench is an evaluation benchmark designed for artificial intelligence (AI) in the healthcare sector. It assesses AI models in real-world scenarios through input from over 250 physicians. The goal of HealthBench is to establish a common standard for evaluating and ensuring the safety of AI performance in healthcare. --- Why it matters: This matters because it provides a standardized framework for testing and validating AI models in healthcare, which can help ensure their reliability and accuracy. Source: https://openai.com/index/healthbench