Across 17 shared benchmarks, Qwen2.5 Instruct 72B scores higher on 1 and Qwen3 VL 235B A22B Reasoning on 15, with 1 level. The widest gap is simpleqa, where Qwen3 VL 235B A22B Reasoning scores 44.4 against 10.3. Tracked API pricing per million tokens: Qwen2.5 Instruct 72B $0.47 in / $0.49 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 (direct, alibaba-official), otherwise the lowest tracked offer.