Across 15 shared benchmarks, DeepSeek-V3 scores higher on 0 and GPT-6 Astra on 15. The widest gap is TauBench V3 - Banking, where GPT-6 Astra scores 43.1 against 4.7. DeepSeek-V3 is the cheaper of the two on tracked API pricing ($0.27 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 (direct, direct), otherwise the lowest tracked offer.