TabPFN-3.5: Technical Report

@misc{jager2026tabpfn35,
  title = {{TabPFN-3.5: Technical Report}},
  author = {Benjamin Jäger and Nick Erickson and Léo Grinsztajn and Felix Birkel and Klemens Flöge and Oscar Key and Kürşat Kaya and Jonas Kübler and Adèle Frankel and Tobias Schröder and Anurag Garg and Jan Hendrik Metzen and David Salinas and Simon Bing and Kristina Collins and Tuana Çelik and Vahid Balazadeh and Lydia Sidhoum and Tomás Pereda and Brendan Roof and Andrej Tschalzev and Siyuan Guo and Philipp Singer and Lennart Purucker and Jake Robertson and Marie Salmon and Philipp Jund and Jerry Chen and Diana Kriuchkova and Arthur Cahu and Eliott Kalfon and Adrian Hayler and Georg Grab and Vitor Monteiro and Lilly Wehrhahn and Dominik Safaric and Clara Cornu and Alan Arazi and Rylee Grace and Simone Alessi and Mihir Manium and Bernhard Schölkopf and Yann LeCun and Madelon Hulsebos and Sauraj Gambhir and Noah Hollmann and Frank Hutter},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.17895},
  eprint = {2609.17895},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.17895},
}

TY  - UNPB
TI  - TabPFN-3.5: Technical Report
AU  - Benjamin Jäger
AU  - Nick Erickson
AU  - Léo Grinsztajn
AU  - Felix Birkel
AU  - Klemens Flöge
AU  - Oscar Key
AU  - Kürşat Kaya
AU  - Jonas Kübler
AU  - Adèle Frankel
AU  - Tobias Schröder
AU  - Anurag Garg
AU  - Jan Hendrik Metzen
AU  - David Salinas
AU  - Simon Bing
AU  - Kristina Collins
AU  - Tuana Çelik
AU  - Vahid Balazadeh
AU  - Lydia Sidhoum
AU  - Tomás Pereda
AU  - Brendan Roof
AU  - Andrej Tschalzev
AU  - Siyuan Guo
AU  - Philipp Singer
AU  - Lennart Purucker
AU  - Jake Robertson
AU  - Marie Salmon
AU  - Philipp Jund
AU  - Jerry Chen
AU  - Diana Kriuchkova
AU  - Arthur Cahu
AU  - Eliott Kalfon
AU  - Adrian Hayler
AU  - Georg Grab
AU  - Vitor Monteiro
AU  - Lilly Wehrhahn
AU  - Dominik Safaric
AU  - Clara Cornu
AU  - Alan Arazi
AU  - Rylee Grace
AU  - Simone Alessi
AU  - Mihir Manium
AU  - Bernhard Schölkopf
AU  - Yann LeCun
AU  - Madelon Hulsebos
AU  - Sauraj Gambhir
AU  - Noah Hollmann
AU  - Frank Hutter
PY  - 2026
DA  - 2026/09/22
PB  - arXiv
DO  - 10.48550/arxiv.2609.17895
UR  - https://arxiv.org/abs/2609.17895
AB  - 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.
ER  -