Codesota · Models · TabPFNPriorLabs (University of Freiburg)1 results · 1 benchmarks

Model card

TabPFN.

PriorLabs (University of Freiburg)open-sourceTransformer (in-context learning)

Pretrained tabular foundation model that performs inference in a single forward pass via in-context learning.

§ 01 · Benchmarks

Every benchmark TabPFN has a recorded score for.

#	Benchmark	Area · Task	Metric	Value	Rank	Date	Source
01	OpenML-CC18	Time Series · Tabular Classification	accuracy	87.0%	#2/5	2025-06-01	source ↗

Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.

§ 02 · Strengths by area

Where TabPFN actually performs.

Time Series

benchmark

avg rank #2.0

§ 03 · Papers

1 paper with results for TabPFN.

2025-06-01· 1 result
ConTextTab: A Semantics-Aware Tabular In-Context Learner
Marco Spinaci

§ 05 · Sources & freshness

Where these numbers come from.

ConTextTab Table 1

result