formalmathatepfl/lean-eval-benchmark download history

formalmathatepfl/lean-eval-benchmark is a text classification dataset on the Hugging Face Hub. In the last 30 days it was downloaded 91 times (33 in the last 7 days), and 233 times in total. It ranks #162,225 among datasets by monthly downloads.

Lean Evaluator Benchmark An out-of-distribution benchmark for models that predict whether a Lean program will compile. Each row contains one prover-generated Lean program and the verdict produced by the real Lean compiler. Dataset summary Rows: 68,932 Lean version: v4.

Open formalmathatepfl/lean-eval-benchmark on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.