FULL STORY

Glass 5.6 Max Tops Medical AI Benchmark

Following a comprehensive clinical evaluation by the ARISE lab, Glass announced that its Glass 5.6 Max model ranked first in the Harvard-Stanford Medical AI Benchmark.

2026-07-21 ~ 2026-07-22 · 2 episodes · 6 posts

Episode 1 · AI Outperforms Doctors in Specialty Consultations (2026-07-21, 3 posts)

A new study by ARISE lab evaluated 45 AI models across 1,100 specialty consultation cases, concluding that AI alone outperformed human doctors in these scenarios.

Episode 2 · Glass 5.6 Max Tops Harvard-Stanford Medical AI Benchmark (2026-07-21, 3 posts)

Glass announced that its Glass 5.6 Max model ranked first with an 88.1% score on the Harvard-Stanford ARISE CPC-Bench. The benchmark evaluates medical AI systems using identical cases and standards, highlighting the model's diagnostic excellence.