Across 28 shared benchmarks, GPT-5 scores higher on 14 and Nemotron 3 Ultra 550B A55B on 14. The widest gap is OmniScience Non-Hallucination, where Nemotron 3 Ultra 550B A55B scores 70.3 against 21. Nemotron 3 Ultra 550B A55B is the cheaper of the two on tracked API pricing ($0.68 against $1.25 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.