vineet-datasets/probe-benchmark-hard90 download history

vineet-datasets/probe-benchmark-hard90 is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 52 times (2 in the last 7 days), and 52 times in total. It ranks #180,833 among datasets by monthly downloads.

PROBE hard90 Human-reviewed hard development benchmark built from benchmark-hard50 plus accepted candidates from benchmark-hard30-review. This bank contains 90 questions: beneath 13, compare 32, count 17, find 28. It is a hard development set, not a balanced or independent holdout. Re

Open vineet-datasets/probe-benchmark-hard90 on Hugging Face

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