Claude Fable 5.1 and Fable 5 both scored perfectly on four jobs, The New Stack reports
The New Stack says Fable 5.1 billed more than twice as much as Fable 5 on the hardest task in its four-job comparison.
TLDR
The New Stack reports that Anthropic shipped Claude Fable 5.1 on September 1, claiming doubled performance in agentic research. The outlet describes a comparison with Fable 5 across four real jobs, tracking every token. Both models scored perfectly, but Fable 5.1 billed more than double Fable 5 on the hardest task.
Combined views
3.5K
4 Sources, first seen 24d ago
2 likes1 saves1 reposts