Across 47 shared benchmarks, Kimi K2 Instruct scores higher on 32 and Qwen3 235B A22B on 14, with 1 level. The widest gap is τ²-Bench, where Kimi K2 Instruct scores 73 against 22.1. Kimi K2 Instruct is the cheaper of the two on tracked API pricing ($0.60 against $0.70 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, alibaba-official), otherwise the lowest tracked offer.