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.
- Epoch AI's FAB benchmark uses photos of three IKEA pieces with deliberate assembly errors.
- GPT-6 Astra scored 80%, versus Claude Opus 4.5's 28% in November 2025.
- Claude Fable 5.1 scored 70% and Claude Opus 5 scored 61%.
- Astra needs about three minutes per photo, too slow for real-time help.
- Chinese open-weight models such as Kimi K3 trail leaders by at least seven months.
- Organizations
- Epoch AIOpenAIAnthropicMoonshot AI
From the original article
1 min read at the-decoder.com
OpenAI's GPT-6 Astra can look at a photo and tell whether an IKEA furniture piece was assembled incorrectly, hitting an 80 percent accuracy rate. Back in November 2025, the best model managed just 28 percent. According to Epoch AI, the speed isn't quite fast enough yet for real-time assembly guidance, but the gap is closing quickly.
By Manuel Uth · the-decoder.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.