OpenAI's GPT-6 Astra can now tell you exactly where you screwed up your IKEA shelf
OpenAI's GPT-6 Astra scores 80% on Epoch AI's furniture-assembly benchmark, up from 28% ten months earlier.
Epoch AI's Furniture Assembly Benchmark photographs three IKEA pieces mid-assembly with deliberate errors and asks models to compare photos with instructions and describe mistakes. In November 2025 the best score was 28% from Claude Opus 4.5. Ten months later OpenAI's GPT-6 Astra reached 80% at about three minutes per photo, ahead of Claude Fable 5.1 at 70% and Claude Opus 5 at 61%. Researchers say it is still too slow for live assembly help, and Chinese open-weight models such as Kimi K3 trail the leaders by at least seven months.
52