Across 24 shared benchmarks, Claude Fable 5.1 scores higher on 23 and Qwen3.6 27B on 1. The widest gap is DeepSWE 1.1, where Claude Fable 5.1 scores 67.4 against 13.3. Qwen3.6 27B is the cheaper of the two on tracked API pricing ($0.60 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.