Across 17 shared benchmarks, GLM-5.1 scores higher on 9 and nvidia-nemotron-3-ultra-550b-a55b-nvfp4 on 8. The widest gap is HLE, where GLM-5.1 scores 52.3 against 26.1. nvidia-nemotron-3-ultra-550b-a55b-nvfp4 is the cheaper of the two on tracked API pricing ($0.60 against $1.38 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, fireworks-ai), otherwise the lowest tracked offer.