Across 10 shared benchmarks, GPT-6 Astra scores higher on 10 and Qwen2.5 Instruct 72B on 0. The widest gap is Artificial Analysis Coding Index, where GPT-6 Astra scores 77.1 against 11.9. Qwen2.5 Instruct 72B is the cheaper of the two on tracked API pricing ($0.47 against $10.00 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 (openai-official, direct), otherwise the lowest tracked offer.