NVIDIA Kumo Relational Model Outperforms Supervised Methods on Relational Benchmarks
NVIDIA Kumo Relational is a pre‑trained relational foundation model that makes predictions directly on enterprise databases . For a predictive query it gathers up to 10,000 historical examples as context and predicts outcomes such as churn, demand, or fraud in a single forward pass . The model requires no task‑specific training, no feature engineering, and no flattening of tables . It is the first few‑shot foundation model to outperform supervised machine learning on common relational benchmarks, beating supervised relational deep‑learning models and expert‑engineered gradient‑boosted tree pipelines across 41 tasks on 15 databases, and surpassing AutoGluon ensembles by 8% in mean reciprocal rank on the SAP SALT benchmark . Kumo Relational scales to databases with over 500 billion rows and is available through NVIDIA’s open‑source GPU‑native structured‑data‑models library or as an NVIDIA NIM .
Why it matters. Enterprises can achieve higher prediction accuracy on massive relational datasets without building custom models, as the model delivers better results than supervised approaches and operates on databases exceeding 500 billion rows .