# OpenAI reports higher everyday-task scores for GPT-6 Astra in new evaluation

_Published Tuesday, November 3, 2026 at 10:08 AM EST · AI · Latest · Tier 2 — Notable_

OpenAI announced a new internal evaluation Monday that it says gives GPT-6 Astra an 80% general-performance score on everyday tasks, compared with 49.3% for GPT-5.2, CNN reported. The tests examine skills such as navigating websites, using personal context from chat history and reaching conclusions that fit a user's needs.

The company surveyed around 4,000 people and asked a smaller group of about 100 users to propose tasks, supply personal context and develop grading criteria. The evaluation covers activities such as apartment hunting and caring for a loved one. Its results measure performance against those criteria; the tasks and desired outcomes can be subjective.

## Sources

- [CNN](https://www.cnn.com/2026/11/02/tech/openai-chatgpt-personal-assistant-ai)

---
Canonical: https://techandbusiness.org/newswire/iXsxK7DAtW0EF3HzJVDk6e
Published: 2026-11-03T15:08:44.388Z
Story chronology: 2026-11-02T17:06:21.700Z
Retrieved: 2026-11-03T17:54:31.056Z
Publisher: Tech & Business (techandbusiness.org)