Glass says ARISE benchmark used identical cases and scoring, where it scored 88.1%

GlassHealthHQ · x · 2026-07-21

Glass says ARISE used the same cases and scoring across systems

Glass says the independent Harvard-Stanford ARISE Medical AI Superintelligence Test (MAST) evaluated every system on the same cases with the same scoring standard, giving clinicians an apples-to-apples comparison.

In that setup, Glass scored 88.1% on CPC-Bench.

Related event: Glass 5.6 Max Tops Harvard-Stanford Medical AI Benchmark(3 posts)→

Original post →

More from Models

Models channel →