Safety overview: GPT-6 Astra

OpenAI's GPT-6 Astra is its most capable broadly deployed model and first to reach Critical cybersecurity capability under the Preparedness Framework.

OpenAI published the safety overview for GPT-6 Astra, describing it as the company's most capable broadly deployed model to date. Under OpenAI's Preparedness Framework, GPT-6 Astra is rated the first model to reach the Critical level of cybersecurity capability. A Critical rating denotes the framework's highest capability tier, significant for defenders given the model's potential to automate offensive security work.

• GPT-6 Astra rated first OpenAI model to reach Critical cybersecurity capability
• Described as OpenAI's most capable broadly deployed model
• Rating determined via OpenAI's Preparedness Framework safety evaluations
• Critical cybersecurity capability relevant to both defenders and offensive threat modeling