Safety overview: GPT-6 Astra Post published:2026-09-04 GPT-6 Astra is our most capable broadly deployed model and our first to reach the Critical level of cybersecurity capability under our Preparedness Framework. Read more articles Previous PostEvalDetectBench: A Benchmark for Measuring Evaluation Awareness in Frontier Language Models Next PostPlayco cut manual fixes 50% prototyping games with GPT-6 Astra