Benchmark
TabArena v0.1
Compare predictive machine-learning methods on curated tabular datasets.
Published leaderboard
Explore scores and evaluation settings on the publisher’s leaderboard.
Open leaderboardCoverage
51 curated IID datasets with multiple splits and classical, neural, and tabular foundation-model approaches.
Methodology
Use shared validation and tuning, distinguishing default, tuned, and ensembled settings. Separate individual models from systems managing their own search and ensembling.