frett/Text2DistBench download history

frett/Text2DistBench is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 60 times (27 in the last 7 days), and 414 times in total. It ranks #164,428 among datasets by monthly downloads.

📌 Overview Text2DistBench is a reading comprehension benchmark for evaluating whether large language models can infer distributional knowledge from natural language evidence. Given metadata and a set of user comments about an entity (e.g., a movie or song), models must infer statistics su

Open frett/Text2DistBench on Hugging Face

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