Across 6 shared benchmarks, Claude 3.5 Sonnet scores higher on 0 and Claude Fable 5.1 on 6. The widest gap is AA Intelligence, where Claude Fable 5.1 scores 56.8 against 10. Claude 3.5 Sonnet is the cheaper of the two on tracked API pricing ($3.00 against $10.00 per million input tokens).
Best tracked score per model per benchmark (default configuration; source-attributed). ↓ marks lower-is-better metrics. Open either model for its full surface, provenance and pricing. Quoted rates are the price-setter row we currently track for each model — its direct or vendor-official listing where one exists (direct, anthropic-official), otherwise the lowest tracked offer.