Epoch AI Finds Models Cannot Yet Reliably Automate Its Knowledge Work
Epoch AI researchers Kelly Hong and Greg Burnham gave six leading models 11 realistic tasks drawn from work at the organization, covering graphic design, short research reports, interactive data tools, AI data-center research, and research design. Claude Fable 5.1 and GPT-6 Astra were roughly tied for the lead, but no model reliably met Epoch’s quality standards; closed-weight models performed best on well-defined tasks, while open-ended work requiring broader judgment remained difficult.
The controlled test directly assesses whether current AI models can replace knowledge workers, and Epoch AI found that current models could not yet meet its work-quality standards.
This source is a digest of several news items (“The Epoch Brief - October 23, 2026”). Find this story in the original.
#Epoch AI#Claude Fable 5.1#GPT-6 Astra#GPT-6.1 Sol#Claude Opus 5.5#Anthropic#OpenAI#Google DeepMind#Gemini 4 Argon#GLM-5.3