AnalysisAI ModelsSeptember 10, 2026

Fable 5.1 vs Fable 5: real-world budget benchmark results

Anthropic's Claude Fable 5.1 scores 52.6% on Terminal-Bench-Science, the benchmark it centered its launch around, where a model gets a terminal and a real scientific research problem to solve independently. The New Stack compares Fable 5.1 and Fable 5 on a real-world budget rather than the spec sheet.

1 source

More stories today

Open the live feed