Glass 5.6 Max claims first place on CPC-Bench with 88.1% on medical diagnosis
GlassHealthHQ · x · 2026-07-21
Glass 5.6 Max tops a medical diagnosis benchmark
Glass says Glass 5.6 Max ranks #1 on CPC-Bench in the Harvard-Stanford ARISE Medical AI Superintelligence Test (MAST), ahead of systems from AMBOSS, OpenAI, Doximity, Anthropic, and Google.
The accompanying chart shows Glass at 88.1%, followed by AMBOSS LISA 2.5 (87.5%), OpenAI GPT-5.5 (86.2%), Doximity Ask 6.1 (81.4%), Anthropic Opus 4.7 (76.7%), and Google Gemini 3.1 Pro (69.3%).
Related event: Glass 5.6 Max Tops Harvard-Stanford Medical AI Benchmark(3 posts)→
More from Models
- Claude Opus 5 is being described as a strong subagent, not a great ideation partner — iskander · 2026-07-27
- Poster says Kimi’s near-term outlook depends on a K3 base model release — _xjdr · 2026-07-27
- Kimi K3 may be strong on cyber, but token efficiency keeps it off UK AISIS — teortaxesTex · 2026-07-27
- European ChatGPT Plus users are now seeing an “Extra High” quality option — PressPlayPlease7 · 2026-07-27
- Opus 5 reportedly aces a car-racing game test on the first try — soumitrashukla9 · 2026-07-27
- Claude Opus 5 arrives at half the price and tops Frontier-Bench claims — GregCook2011 · 2026-07-27