Across 21 shared benchmarks, Claude Fable 5.1 scores higher on 21 and Gemma 4 26B A4B on 0. The widest gap is SWE-bench Pro, where Claude Fable 5.1 scores 81.2 against 13.8. Gemma 4 26B A4B is the cheaper of the two on tracked API pricing ($0.13 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 (anthropic-official, direct), otherwise the lowest tracked offer.