Announcement
Epoch introduces Automation Reports to test AI on its own work
Epoch says Claude Fable 5.1 and GPT-6 Astra lead, but remain far from fully automating its work.
TLDR
Epoch introduced Automation Reports to evaluate frontier AI models on realistic, open-ended tasks drawn from its own work. It says Claude Fable 5.1 and GPT-6 Astra lead, though both remain far from fully automating that work.
Combined views
12K
5 Sources, first seen ago
