Across 15 shared benchmarks, GPT-5.6 Sol scores higher on 9 and Hy4 on 6. The widest gap is Program Bench, where GPT-5.6 Sol scores 77.6 against 17.5. Hy4 is the cheaper of the two on tracked API pricing ($0.83 against $4.00 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, tencent), otherwise the lowest tracked offer.