Across 16 shared benchmarks, DeepSeek-V4-Pro scores higher on 15 and Qwen3 VL 235B A22B Reasoning on 1. The widest gap is Terminal-Bench Hard, where DeepSeek-V4-Pro scores 46.2 against 11.4. Tracked API pricing per million tokens: DeepSeek-V4-Pro $1.32 in / $3.96 out, Qwen3 VL 235B A22B Reasoning $0.40 in / $4.00 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 (deepseek-official, alibaba-official), otherwise the lowest tracked offer.