Across 30 shared benchmarks, Kimi K2 Instruct scores higher on 3 and MiniMax M2.7 on 27. The widest gap is browsecomp, where MiniMax M2.7 scores 54.1 against 14.1. MiniMax M2.7 is the cheaper of the two on tracked API pricing ($0.30 against $0.60 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, direct), otherwise the lowest tracked offer.