Across 44 shared benchmarks, Claude Sonnet 4.6 scores higher on 37 and MiniMax M2.7 on 6, with 1 level. The widest gap is critpt, where Claude Sonnet 4.6 scores 3.1 against 0.6. MiniMax M2.7 is the cheaper of the two on tracked API pricing ($0.30 against $3.00 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.