Across 23 shared benchmarks, GPT-5 scores higher on 4 and Qwen3.8 Max Preview on 19. The widest gap is critpt, where Qwen3.8 Max Preview scores 20 against 5.7. Tracked API pricing per million tokens: GPT-5 $1.25 in / $10.00 out, Qwen3.8 Max Preview $2.00 in / $6.00 out.
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.