Year: 2026
Type: preprint
Abstract: We introduce TabPFN-3.5, our new flagship Tabular Foundation Model. It significantly outperforms its predecessor, TabPFN-3, and all existing baselines across a broad range of tabular problems. TabPFN-3.5 sets a new state of the art on standard tabular prediction in TabArena, and extends it to the data practitioners encounter in practice: non-i.i.d. data with temporal or grouped splits, tables with strings, text and images, high-cardinality categorical features, and wide tables with many features. These gains carry over to our task-specific harnesses: state of the art on relational data and stronger time-series forecasting. For faster inference, our variant TabPFN-3.5-Fast runs up to 3x faster than TabPFN-3 while keeping most of the accuracy gains. In addition, we upgrade TabPFN-3.5-Plus, expanding our multimodal capabilities with advanced text and date handling alongside proprietary inference optimizations. Finally, we release a new version of our Thinking mode, TabPFN-3.5-Thinking, which scales inference-time computation to push the state of the art further. It benefits from our stronger base model and from inference-time improvements that make it up to 12x faster than TabPFN-3-Thinking.
Source: arXiv (Cornell University)
Authors: Jäger, Benjamin, Erickson, Nick, Grinsztajn, Léo, Birkel, Felix, Flöge, Klemens, Key, Oscar, Kaya, Kürşat, Kübler, Jonas, Frankel, Adèle, Schröder, Tobias, Garg, Anurag, Metzen, Jan Hendrik, Salinas, David, Bing, Simon, Collins, Kristina, Çelik, Tuana, Balazadeh, Vahid, Sidhoum, Lydia, Pereda, Tomás, Roof, Brendan, Tschalzev, Andrej, Guo, Siyuan, Singer, Philipp, Purucker, Lennart, Robertson, Jake, Salmon, Marie, Jund, Philipp, Chen, Jerry, Kriuchkova, Diana, Cahu, Arthur, Kalfon, Eliott, Hayler, Adrian, Grab, Georg, Monteiro, Vitor, Wehrhahn, Lilly, Safaric, Dominik, Cornu, Clara, Arazi, Alan, Grace, Rylee, Alessi, Simone, Manium, Mihir, Schölkopf, Bernhard, LeCun, Yann, Hulsebos, Madelon, Gambhir, Sauraj, Hollmann, Noah, Hutter, Frank
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7213514489
Cites:
Cited by:
Related to: