Evaluating chain-of-thought monitorability
OpenAI Blog
December 18, 2025
OpenAI introduces a new framework and evaluation suite for chain-of-thought monitorability, covering 13 evaluations across 24 environments. Our findings show that monitoring a model’s internal reasoning is far more effective than monitoring outputs alone, offering a promising path toward scalable control as AI systems grow more capable.
Verticals
airesearch
Originally published on OpenAI Blog on 12/18/2025