Across 34 shared benchmarks, GPT-5.4 scores higher on 11 and Qwen3.8 Max Preview on 23. The widest gap is OmniScience Non-Hallucination, where Qwen3.8 Max Preview scores 58.3 against 17.4. Qwen3.8 Max Preview is the cheaper of the two on tracked API pricing ($2.00 against $2.50 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.