Across 23 shared benchmarks, Claude 3.5 Sonnet scores higher on 2 and Qwen3 VL 235B A22B Reasoning on 21. The widest gap is HLE, where Qwen3 VL 235B A22B Reasoning scores 13.6 against 3.9. Qwen3 VL 235B A22B Reasoning is the cheaper of the two on tracked API pricing ($0.40 against $3.00 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.