Across 27 shared benchmarks, Claude 3.5 Sonnet scores higher on 6 and Kimi K2 Instruct on 19, with 2 level. The widest gap is AIME 2025, where Kimi K2 Instruct scores 57 against 7.4. Kimi K2 Instruct is the cheaper of the two on tracked API pricing ($0.60 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 (direct, direct), otherwise the lowest tracked offer.