Across 12 shared benchmarks, Qwen2.5 Instruct 72B scores higher on 0 and Qwen3.8 Max Preview on 12. The widest gap is Artificial Analysis Coding Index, where Qwen3.8 Max Preview scores 71.8 against 11.9. Qwen2.5 Instruct 72B is the cheaper of the two on tracked API pricing ($0.47 against $2.00 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, alibaba-official), otherwise the lowest tracked offer.