Across 16 shared benchmarks, nvidia-nemotron-3-ultra-550b-a55b-nvfp4 scores higher on 10 and Qwen 3.5 397B 17B on 6. The widest gap is τ³-Bench, where nvidia-nemotron-3-ultra-550b-a55b-nvfp4 scores 93.6 against 20.9.
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.