Eric Topol says GPT-5.5 Pro scored 79/100 on medical benchmark but remains below clinical deployment threshold
Separately, Sophont released Medmarks v1.0 to automate medical evaluations.
Combined views
88.4K
8 posts, first seen 65d ago
430 likes23 comments108 saves
Eric Topol says GPT-5.5 Pro scored 79/100 on medical benchmark but remains below clinical deployment threshold
Separately, Sophont released Medmarks v1.0 to automate medical evaluations.