Across 28 shared benchmarks, DeepSeek-R1 scores higher on 6 and MiniMax M2.7 on 22. The widest gap is AA Agentic Index, where MiniMax M2.7 scores 25.9 against 3.1. MiniMax M2.7 is the cheaper of the two on tracked API pricing ($0.30 against $1.35 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.