OpenAI’s GPT-6 Astra can now use photos to determine whether IKEA furniture has been assembled incorrectly, with accuracy reaching 80%, according to Techub News citing The Decoder. The result marks a sharp improvement from November 2025, when the best-performing model managed only 28% accuracy on the same kind of task. Epoch AI said the model’s speed still falls short of what would be needed for real-time assembly guidance. Even so, the gap is narrowing quickly, pointing to steady progress in visual reasoning tied to practical household tasks. The update highlights how fast model performance has improved on image-based error detection, even if the system is not yet fast enough to guide users step by step during live assembly.
OpenAI’s GPT-6 Astra can now identify, from photos, whether IKEA furniture has been assembled incorrectly, reaching 80% accuracy, according to Techub News, which cited The Decoder.
That marks a substantial jump from November 2025, when the best model achieved only 28% accuracy. Research group Epoch AI said the system is still not fast enough to support real-time assembly guidance, though the gap is closing quickly.
This article was originally published by Bit.Fan. For more cryptocurrency news and market insights, visit www.bit.fan. Disclaimer:
The market information, project data, and third-party content displayed on this platform are for industry information sharing only and do not constitute any form of investment advice or return commitment.
Cryptocurrency trading carries high risks. Users should fully assess their risk tolerance and make independent decisions. All profits, losses, and legal responsibilities are borne by the users themselves.
