AIThe Decoderabout 1 hour ago
GPT-6 Astra Tops Furniture Assembly Benchmark
1 min read
Epoch AI's Furniture Assembly Benchmark photographs three IKEA pieces during assembly with deliberate errors, and models identify the mistakes. In November 2025, Claude Opus 4.5 scored 28 percent; ten months later, OpenAI's GPT-6 Astra reaches 80 percent at three minutes per photo. Claude Fable 5.1 follows at 70 percent, Claude Opus 5 at 61 percent, and Chinese open-weight models like Kimi K3 trail leaders by at least seven months.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
