Tag: AI benchmarking
Stanford and Harvard launch MAST framework for tracking clinical AI progress
Stanford and Harvard researchers debut MAST v1.0, a new benchmark framework for measuring clinical AI performance across real healthcare tasks.
White House convenes clinical AI experts for standards sprint on evaluation
The White House, FDA, and ONC launch a month-long effort to create consensus principles for clinical AI benchmarking.
Johns Hopkins finds frontier AI agents fail most complex health tasks
A benchmark test found leading AI agents completed only 28% of healthcare administrative tasks on a first attempt.