tabpfn_3_5

Model Overview

TabPFN-3.5 is a transformer-based foundation model that uses in-context learning to solve tabular prediction problems in a forward pass. One checkpoint serves both classification and regression. Inference code can be found at https://github.com/PriorLabs/TabPFN.

Getting started

First, install the inference package:

pip install tabpfn

Fitting a classifier and predicting looks like this:

from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from tabpfn import TabPFNClassifier
from tabpfn.constants import ModelVersion

X, y = load_breast_cancer(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=42)

clf = TabPFNClassifier.create_default_for_version(ModelVersion.V3_5)
clf.fit(X_train, y_train)
prediction_probabilities = clf.predict_proba(X_test)
predictions = clf.predict(X_test)
print("Accuracy", accuracy_score(y_test, predictions))

TabPFNRegressor works the same way, off the same checkpoint. For more examples, see the github repo: https://github.com/PriorLabs/TabPFN.

Checkpoints

To use a specific checkpoint, pass its filename via model_path:

from tabpfn import TabPFNClassifier

clf = TabPFNClassifier(model_path="tabpfn-v3.5-20260909_multiclass.safetensors")

Every checkpoint ships with basic text and datetime column handling enabled (TRANSFORM_TEXT, TRANSFORM_DATES) and a feature limit of 20,000.

Developers & Affiliations

Developed by Prior Labs.

Intended Use

Regression and classification tasks on structured tabular data, including string and datetime columns.

Not Intended Use

• Not suitable for unstructured data such as images.

Training Data and Priors

TabPFN-3.5 is trained purely on synthetic tabular tasks.

Ethical Considerations

Having been trained purely on synthetic datasets, TabPFN-3.5 is free from dataset leakage from the pretraining stage. However, like for any other tabular prediction method, when applied to high-risk use cases, users should ensure that the labelled data is free of biases.

Licensing

Model weights released under tabpfn-3-5-license-v1.0.

The license is designed to be permissive for research and limited internal evaluation. It explicitly allows testing, evaluation, and internal benchmarking, so an organization can download the model and run preliminary assessments on its own datasets. The key restriction is that the model, its derivatives, and its outputs cannot be used for any commercial or production purpose. This includes, but is not limited to, revenue-generating products, competitive benchmarking for procurement, client deliverables, or using the model’s results for internal commercial decision-making. For all production use cases, we offer a Commercial Enterprise License. This provides access to our proprietary high-speed inference engine, dedicated support, integration tooling, and other internal models. Please contact us at [email protected] for commercial licensing inquiries.

Version

v1.0: initial release.