Across 33 shared benchmarks, Claude Opus 5 scores higher on 27 and Qwen3.8 Max Preview on 6. The widest gap is OmniScience Accuracy, where Claude Opus 5 scores 60.9 against 31.9. Qwen3.8 Max Preview is the cheaper of the two on tracked API pricing ($2.00 against $5.00 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.