Across 22 shared benchmarks, Claude Fable 5.1 scores higher on 21 and Gemini 3 Pro on 1. The widest gap is OmniScience Non-Hallucination, where Claude Fable 5.1 scores 34.4 against 10. Gemini 3 Pro is the cheaper of the two on tracked API pricing ($2.00 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 (anthropic-official, direct), otherwise the lowest tracked offer.