Across 16 shared benchmarks, DeepSeek-V4-Flash scores higher on 15 and nvidia-nemotron-3-ultra-550b-a55b-nvfp4 on 1. The widest gap is τ³-Bench, where nvidia-nemotron-3-ultra-550b-a55b-nvfp4 scores 93.6 against 26.7. DeepSeek-V4-Flash is the cheaper of the two on tracked API pricing ($0.44 against $0.60 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 (deepseek-official, fireworks-ai), otherwise the lowest tracked offer.