Across 30 shared benchmarks, GPT-5.1 scores higher on 29 and Kimi K2 Instruct on 1. The widest gap is vectara_avg_summary_length, where GPT-5.1 scores 254.4 against 59.2. 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 (direct, direct), otherwise the lowest tracked offer.