MacrOData supplies three large, curated benchmark suites totaling 2,446 datasets for tabular outlier detection, complete with standardized splits, metadata, and a public leaderboard.
hub Baseline reference
TabArena: A Living Benchmark for Machine Learning on Tabular Data
Baseline reference. 56% of citing Pith papers use this work as a benchmark or comparison.
30
Pith papers citing it
158
external citations · Pith
Baseline
56% of classified citations
abstract
With the growing popularity of deep learning and foundation models for tabular data, the need for standardized and reliable benchmarks is higher than ever. However, current benchmarks are static. Their design is not updated even if flaws are discovered, model versions are updated, or new models are released. To address this, we introduce TabArena, the first continuously maintained living tabular benchmarking system. To launch TabArena, we manually curate a representative collection of datasets and well-implemented models, conduct a large-scale benchmarking study to initialize a public leaderboard, and assemble a team of experienced maintainers. Our results highlight the influence of validation method and ensembling of hyperparameter configurations to benchmark models at their full potential. While gradient-boosted trees are still strong contenders on practical tabular datasets, we observe that deep learning methods have caught up under larger time budgets with ensembling. At the same time, foundation models excel on smaller datasets. Finally, we show that ensembles across models advance the state-of-the-art in tabular machine learning. We observe that some deep learning models are overrepresented in cross-model ensembles due to validation set overfitting, and we encourage model developers to address this issue. We launch TabArena with a public leaderboard, reproducible code, and maintenance protocols to create a living benchmark available at https://tabarena.ai.
hub tools
citation-role summary
dataset 5
background 4
citation-polarity summary
representative citing papers
TabPrep is a new feature engineering pipeline that targets three data patterns and improves performance of tree-based, neural, linear, and foundation models on tabular benchmarks, often more than model architecture changes.
PRAXIS approximates decision tree Rashomon sets with major runtime and memory improvements while recovering nearly the full set on tested data.
Reasoning LLMs with minimal tools for tree construction and analysis induce decision trees that outperform CART, compete with ensembles on low-resource tabular data, and provide human-readable reasoning traces.
MulTaBench is a new collection of 40 image-tabular and text-tabular datasets designed to test target-aware representation tuning in multimodal tabular models.
TFM-Retouche is an architecture-agnostic input-space residual adapter that improves tabular foundation model accuracy on 51 datasets by learning input corrections through the frozen backbone, with an identity guard to fall back to the original model.
Agentic-imodels evolves scikit-learn regressors via an autoresearch loop to jointly boost predictive performance and LLM-simulatability, improving downstream agentic data science tasks by up to 73% on the BLADE benchmark.
RamanBench unifies 74 datasets into the first large-scale reproducible benchmark for ML on Raman spectra, finding tabular foundation models outperform baselines but no method generalizes across datasets.
TabDistill distills feature interactions from tabular foundation models via post-hoc attribution and inserts them into GAMs, yielding consistent predictive gains.
OmniTabBench shows no single model family dominates tabular tasks and maps performance advantages to specific dataset properties like size and skewness.
TS-Arena is a live pre-registration platform that evaluates time series forecasts on future data streams to eliminate information leakage.
Multistage defer trees chain sparse decision trees with deferral to match complex ensemble accuracy while routing most samples through one or few interpretable trees.
Proposes TopoAgent, an LLM agent framework that automatically selects and configures topological descriptors from persistent homology for medical image analysis without task-specific training.
CRUMB speeds up PFN inference on large tabular datasets by clustering queries and selecting MMD-matched context subsets, outperforming prior selection methods on the 51-dataset TabArena benchmark across three architectures while handling covariate drift.
LimiX-2M outperforms larger TabPFN-v2 and TabICL models on tabular benchmarks by expanding scalars into RBF features and using a reordered S->N->F attention block.
LLMTabBench evaluates LLMs on zero- and few-shot binary tabular classification and reports that zero-shot can outperform few-shot due to example conflicts with model priors while performance drops beyond a complexity threshold.
O'Prior, a compositional synthetic prior with hierarchical SCMs, realism engines, stress modules, and curriculum protocols, improves tabular foundation model accuracy and robustness on real benchmarks when architecture and compute are held fixed.
TabPFN-3 scales tabular foundation models to 1M rows with synthetic pretraining, test-time compute, and benchmark-leading performance on tabular, relational, and tabular-text tasks while being up to 20x faster than TabPFN-2.5.
xRFM merges kernel-based feature learning with tree structures for scalable, interpretable tabular modeling and reports top performance on 100 regression and competitive results on 200 classification datasets versus 31 baselines including GBDTs and TabPFNv2.
BoostLLM trains sequential PEFT adapters in a boosting framework with tree path inputs to improve LLM performance on few-shot tabular classification, matching or exceeding XGBoost.
Tabular foundation models achieve high accuracy in molecular property prediction through in-context learning, with up to 100% win rates on MoleculeACE tasks when paired with CheMeleon embeddings.
Muon optimizer outperforms AdamW across 17 tabular datasets when training MLPs under a shared protocol.
TabPFN-2.5 scales tabular foundation models to 20x larger datasets, outperforms tuned tree models on TabArena, achieves near-perfect win rates against default XGBoost, and adds a distillation engine for fast production deployment.
Reject-to-remeasure combines probabilistic ML on soil spectra with uncertainty-guided rejection to meet user accuracy targets on a Québec dataset while lowering measurement costs.
citing papers explorer
-
MacrOData: New Benchmarks of Thousands of Datasets for Tabular Outlier Detection
MacrOData supplies three large, curated benchmark suites totaling 2,446 datasets for tabular outlier detection, complete with standardized splits, metadata, and a public leaderboard.
-
TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks
TabPrep is a new feature engineering pipeline that targets three data patterns and improves performance of tree-based, neural, linear, and foundation models on tabular benchmarks, often more than model architecture changes.
-
From Rashomon Theory to PRAXIS: Efficient Decision Tree Rashomon Sets
PRAXIS approximates decision tree Rashomon sets with major runtime and memory improvements while recovering nearly the full set on tested data.
-
Talking Trees: Reasoning-Assisted Induction of Decision Trees for Tabular Data
Reasoning LLMs with minimal tools for tree construction and analysis induce decision trees that outperform CART, compete with ensembles on low-resource tabular data, and provide human-readable reasoning traces.
-
MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image
MulTaBench is a new collection of 40 image-tabular and text-tabular datasets designed to test target-aware representation tuning in multimodal tabular models.
-
TFM-Retouche: A Lightweight Input-Space Adapter for Tabular Foundation Models
TFM-Retouche is an architecture-agnostic input-space residual adapter that improves tabular foundation model accuracy on 51 datasets by learning input corrections through the frozen backbone, with an identity guard to fall back to the original model.
-
Agentic-imodels: Evolving agentic interpretability tools via autoresearch
Agentic-imodels evolves scikit-learn regressors via an autoresearch loop to jointly boost predictive performance and LLM-simulatability, improving downstream agentic data science tasks by up to 73% on the BLADE benchmark.
-
RamanBench: A Large-Scale Benchmark for Machine Learning on Raman Spectroscopy
RamanBench unifies 74 datasets into the first large-scale reproducible benchmark for ML on Raman spectra, finding tabular foundation models outperform baselines but no method generalizes across datasets.
-
Selecting Feature Interactions for Generalized Additive Models by Distilling Foundation Models
TabDistill distills feature interactions from tabular foundation models via post-hoc attribution and inserts them into GAMs, yielding consistent predictive gains.
-
OmniTabBench: Mapping the Empirical Frontiers of GBDTs, Neural Networks, and Foundation Models for Tabular Data at Scale
OmniTabBench shows no single model family dominates tabular tasks and maps performance advantages to specific dataset properties like size and skewness.
-
TS-Arena -- A Live Forecast Pre-Registration Platform
TS-Arena is a live pre-registration platform that evaluates time series forecasts on future data streams to eliminate information leakage.
-
Multistage Defer Trees for Hybrid Interpretability: If at First You Can't Succeed, Tree Again
Multistage defer trees chain sparse decision trees with deferral to match complex ensemble accuracy while routing most samples through one or few interpretable trees.
-
TopoAgent: An Agentic Framework for Automated Topology Learning in Medical Imaging
Proposes TopoAgent, an LLM agent framework that automatically selects and configures topological descriptors from persistent homology for medical image analysis without task-specific training.
-
CRUMB: Efficient Prior Fitted Network Inference via Distributionally Matched Context Batching
CRUMB speeds up PFN inference on large tabular datasets by clustering queries and selecting MMD-matched context subsets, outperforming prior selection methods on the 51-dataset TabArena benchmark across three architectures while handling covariate drift.
-
LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models
LimiX-2M outperforms larger TabPFN-v2 and TabICL models on tabular benchmarks by expanding scalars into RBF features and using a reordered S->N->F attention block.
-
LLMTabBench: Evaluating LLMs on Binary Tabular Classification From Zero to Few Shots
LLMTabBench evaluates LLMs on zero- and few-shot binary tabular classification and reports that zero-shot can outperform few-shot due to example conflicts with model priors while performance drops beyond a complexity threshold.
-
Shaping the Prior: How Synthetic Task Distributions Determine Tabular Foundation Model Quality
O'Prior, a compositional synthetic prior with hierarchical SCMs, realism engines, stress modules, and curriculum protocols, improves tabular foundation model accuracy and robustness on real benchmarks when architecture and compute are held fixed.
-
TabPFN-3: Technical Report
TabPFN-3 scales tabular foundation models to 1M rows with synthetic pretraining, test-time compute, and benchmark-leading performance on tabular, relational, and tabular-text tasks while being up to 20x faster than TabPFN-2.5.
-
xRFM: Accurate, scalable, and interpretable feature learning models for tabular data
xRFM merges kernel-based feature learning with tree structures for scalable, interpretable tabular modeling and reports top performance on 100 regression and competitive results on 200 classification datasets versus 31 baselines including GBDTs and TabPFNv2.
-
BoostLLM: Boosting-inspired LLM Fine-tuning for Few-shot Tabular Classification
BoostLLM trains sequential PEFT adapters in a boosting framework with tree path inputs to improve LLM performance on few-shot tabular classification, matching or exceeding XGBoost.
-
Tabular foundation models for in-context prediction of molecular properties
Tabular foundation models achieve high accuracy in molecular property prediction through in-context learning, with up to 100% win rates on MoleculeACE tasks when paired with CheMeleon embeddings.
-
Benchmarking Optimizers for MLPs in Tabular Deep Learning
Muon optimizer outperforms AdamW across 17 tabular datasets when training MLPs under a shared protocol.
-
TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Models
TabPFN-2.5 scales tabular foundation models to 20x larger datasets, outperforms tuned tree models on TabArena, achieves near-perfect win rates against default XGBoost, and adds a distillation engine for fast production deployment.
-
Rejections Based on Predictive Uncertainty Enable Reliable Routine Soil Spectroscopy
Reject-to-remeasure combines probabilistic ML on soil spectra with uncertainty-guided rejection to meet user accuracy targets on a Québec dataset while lowering measurement costs.
-
Rank Intervals for Leaderboards: A Hierarchical Framework for Model Evaluation
A hierarchical framework generates statistically valid task-level rank confidence intervals via pairwise comparisons and leaderboard-level rank prediction intervals via conformal prediction.
-
High Performance, Low Reliability: Uncertainty Benchmarking for Tabular Foundation Models
TFMs achieve top AUC on TALENT but lower conditional coverage (SSCS) than GBDTs under conformal prediction, revealing a performance-uncertainty trade-off.
-
TabCF: Distributional Control Function Estimation with Tabular Foundation Models
TabCF is a tuning-light method using tabular foundation models for control function regression to estimate distributional causal effects such as interventional means and quantiles.
-
Heterogeneous Scientific Foundation Model Collaboration
Eywa enables language-based agentic AI systems to collaborate with specialized scientific foundation models for improved performance on structured data tasks.
-
Noise Immunity in In-Context Tabular Learning: An Empirical Robustness Analysis of TabPFN's Attention Mechanisms
TabPFN maintains high ROC-AUC and structured attention under controlled additions of irrelevant features, nonlinear correlations, and mislabeled targets in binary classification.
-
Evaluating Local Explainability Metrics for Machine Learning Models on Tabular Data
Benchmark of local explainability methods on tabular data finds explanation quality driven primarily by dataset complexity rather than model predictive performance.