Across 44 shared benchmarks, Gemini 2.5 Pro scores higher on 30 and Kimi K2 Instruct on 13, with 1 level. The widest gap is AA Agentic Index, where Kimi K2 Instruct scores 37.7 against 7.2. Kimi K2 Instruct is the cheaper of the two on tracked API pricing ($0.60 against $1.25 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 (google-official, direct), otherwise the lowest tracked offer.