TabPFN-3.5 Plus is Now Available in SAP AI Core 

SAP announced the availability of the new TabPFN-3.5 model from Prior Labs, an SAP company—marking the next leap in tabular AI.

According to SAP, this model gives organizations access to unmatched tabular AI predictions on structured business data without model training or tuning. For SAP customers, TabPFN-3.5 Plus is now available in SAP AI Core.

With TabPFN-3.5, SAP customers can work with data as it exists in their systems. Missing values, mixed data types and inconsistent fields are handled by the model, returning accurate predictions without preprocessing. 

This newest model from Prior Labs’ family of tabular AI models uses in-context learning to make predictions from raw tabular data, handling columns with thousands of distinct values, such as product codes or customer identifiers, and mixed data types natively, without the trial-and-error configuration that traditional models require, said SAP.

TabPFN-3.5 Plus is the most accurate and scalable tabular foundation model available today, based on TabArena and BeyondArena, two external benchmarks designed to evaluate predictions over real-world data, said SAP.

“Real-world data is rarely perfect. Datasets often contain complex relationships and varying conditions that make traditional machine learning difficult. TabPFN-3.5 is specifically built for these challenges, providing industry-leading accuracy and scalability for tabular data with less manual effort—making it the most effective tabular AI model in the industry to date,” said Philipp Herzig, chief technology officer, SAP SE. “With TabPFN-3.5 and the SAP-RPT model family, customers get accurate predictions from labeled business data in minutes, with no training required. For us, tabular AI is not a supporting feature of the Autonomous Enterprise, it is the foundation.”