Across 36 shared benchmarks, Gemini 3.1 Pro scores higher on 13 and Qwen3.8 Max Preview on 23. The widest gap is AA-Omniscience, where Gemini 3.1 Pro scores 32.9 against 3.4. Both cost $2.00 per million input tokens on tracked API pricing; Qwen3.8 Max Preview is cheaper on output ($6.00 against $12.00).
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 (google-official, alibaba-official), otherwise the lowest tracked offer.