AI agent capabilities
The Decoder
GPT-6 Astra earns nearly three times as much as Claude Fable 5.1 on Andon Labs' Vending-Bench agent benchmark and refuses illegal price-fixing deals that Fable agrees to. On drone control, Astra is the first model to beat the human baseline on all five subtasks, including finding and following individual people.
GPT-6 Astra pilots a surveillance drone and runs a business on its own
GPT-6 Astra outperforms Claude on business agent tasks and drone control, surpassing human performance on the latter.
The Decoder
The Verge
TechCrunch
