Fable 5.1 vs. Fable 5 on a real-world budget
The New Stack reports that Claude Fable 5.1 passed one of five tasks on a modest budget, but its failures cost less.
TLDR
Claude Fable 5.1 more than doubled its predecessor’s benchmark score, according to The New Stack. On a modest budget, however, it passed one of five tasks. The outlet reports that its failures cost less.
Combined views
489
1 Source, first seen 1d ago
Fable 5.1 vs. Fable 5 on a real-world budget
The New Stack reports that Claude Fable 5.1 passed one of five tasks on a modest budget, but its failures cost less.
TLDR
Claude Fable 5.1 more than doubled its predecessor’s benchmark score, according to The New Stack. On a modest budget, however, it passed one of five tasks. The outlet reports that its failures cost less.