Model Releases
Astra achieves state-of-the-art results on Agents’ Last Exam, AutomationBench, and ScreenSpot Pro, benchmarks for computer workflow tasks ac…
OpenAI’s new language‑model system **Astra** has achieved state‑of‑the‑art performance on three key workflow benchmarks: the Agents’ Last Exam, AutomationBench, and ScreenSpot Pro. These suites evalua
OpenAI’s new language‑model system Astra has achieved state‑of‑the‑art performance on three key workflow benchmarks: the Agents’ Last Exam, AutomationBench, and ScreenSpot Pro. These suites evaluate automated computer tasks across diverse professional domains, indicating that Astra excels at complex, real‑world work‑flows compared to previous models.
Related
- GPT-6 Astra is the most intelligent and aligned model in the world, and sets a new state of the art for computer use, browsing, software eng…
- Agents' Last Exam
- Astra is our most aligned model, with substantial improvements in understanding user intent.
Source: OpenAI (X) | 2026-09-03