OpenAI says GPT-6 Astra rated clinically safe on 99% of 325 medical inbox tasks

Polymarket · x · 2026-11-17

OpenAI revealed that GPT-6 Astra's work was rated "clinically safe" on 99% of 325 reviewed medical inbox tasks, a notable safety data point for the model in real healthcare workflows.

Original post →

More from Models

Models channel →