A shared playbook for trustworthy third party evaluations

This document outlines OpenAI's framework and recommendations for conducting independent third-party evaluations of AI systems to ensure trustworthiness and accountability. It establishes shared standards and practices for external evaluators assessing AI capabilities, safety, and alignment to improve transparency in the AI development process. The playbook serves as a foundational guide for creating consistent, reliable evaluation methodologies across the industry.

Source: OpenAI | 2026-05-29