{
  "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.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.17895",
  "author_total": 47,
  "authors": [
    {
      "name": "Benjamin Jäger"
    },
    {
      "name": "Nick Erickson"
    },
    {
      "name": "Léo Grinsztajn"
    },
    {
      "name": "Felix Birkel"
    },
    {
      "name": "Klemens Flöge"
    },
    {
      "name": "Oscar Key"
    },
    {
      "name": "Kürşat Kaya"
    },
    {
      "name": "Jonas Kübler"
    },
    {
      "name": "Adèle Frankel"
    },
    {
      "name": "Tobias Schröder"
    },
    {
      "name": "Anurag Garg"
    },
    {
      "name": "Jan Hendrik Metzen"
    },
    {
      "name": "David Salinas"
    },
    {
      "name": "Simon Bing"
    },
    {
      "name": "Kristina Collins"
    },
    {
      "name": "Tuana Çelik"
    },
    {
      "name": "Vahid Balazadeh"
    },
    {
      "name": "Lydia Sidhoum"
    },
    {
      "name": "Tomás Pereda"
    },
    {
      "name": "Brendan Roof"
    },
    {
      "name": "Andrej Tschalzev"
    },
    {
      "name": "Siyuan Guo"
    },
    {
      "name": "Philipp Singer"
    },
    {
      "name": "Lennart Purucker"
    },
    {
      "name": "Jake Robertson"
    },
    {
      "name": "Marie Salmon"
    },
    {
      "name": "Philipp Jund"
    },
    {
      "name": "Jerry Chen"
    },
    {
      "name": "Diana Kriuchkova"
    },
    {
      "name": "Arthur Cahu"
    },
    {
      "name": "Eliott Kalfon"
    },
    {
      "name": "Adrian Hayler"
    },
    {
      "name": "Georg Grab"
    },
    {
      "name": "Vitor Monteiro"
    },
    {
      "name": "Lilly Wehrhahn"
    },
    {
      "name": "Dominik Safaric"
    },
    {
      "name": "Clara Cornu"
    },
    {
      "name": "Alan Arazi"
    },
    {
      "name": "Rylee Grace"
    },
    {
      "name": "Simone Alessi"
    },
    {
      "name": "Mihir Manium"
    },
    {
      "name": "Bernhard Schölkopf"
    },
    {
      "name": "Yann LeCun"
    },
    {
      "name": "Madelon Hulsebos"
    },
    {
      "name": "Sauraj Gambhir"
    },
    {
      "name": "Noah Hollmann"
    },
    {
      "name": "Frank Hutter"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9sbmkeg6ydc6b.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.17895",
  "fulltext_url": null,
  "id": "9sbmkeg6ydc6b",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.17895",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|Machine Learning and Data Classification"
    ]
  ],
  "openalex": "W7213514489",
  "pdf_url": "https://arxiv.org/pdf/2609.17895",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-22",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/9sbmkeg6ydc6b.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:24:06Z",
      "native_id": "2609.17895",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.17895"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "TabPFN-3.5: Technical Report",
  "title_text": "TabPFN-3.5: Technical Report",
  "type": "preprint",
  "updated_at": "2026-11-06T18:21:10Z",
  "url": "https://research.draconitic.com/paper/9sbmkeg6ydc6b",
  "venue": "arXiv",
  "versions": []
}