lighteval/logiqa_harness download history

lighteval/logiqa_harness is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 724 times (28 in the last 7 days), and 3,616 times in total. It ranks #24,710 among datasets by monthly downloads.

LogiQA is a dataset for testing human logical reasoning. It consists of 8,678 QA instances, covering multiple types of deductive reasoning. Results show that state- of-the-art neural models perform by far worse than human ceiling. The dataset can also serve as a benchmark for reinvestigating logical

Open lighteval/logiqa_harness on Hugging Face

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