EPFL-LARA/lean-evaluation-benchmark download history
EPFL-LARA/lean-evaluation-benchmark is a text classification dataset on the Hugging Face Hub. In the last 30 days it was downloaded 451 times (34 in the last 7 days), and 733 times in total. It ranks #49,532 among datasets by monthly downloads.
Evaluation benchmark The paper's evaluation benchmark for learned Lean 4 evaluators contains 68,932 deduplicated candidate programs from three public provers. Each row contains a complete source program and the acceptance label obtained with Lean v4.15.0. Subset Programs Valid
Open EPFL-LARA/lean-evaluation-benchmark on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.