kensho/WILD-raw download history
kensho/WILD-raw is a text classification dataset on the Hugging Face Hub. In the last 30 days it was downloaded 227 times (75 in the last 7 days), and 2,756 times in total. It ranks #60,993 among datasets by monthly downloads.
Dataset to accompany the paper Cost-Efficient Estimation of General Abilities Across Benchmarks. WILD-raw: Wide-scale Item Level Dataset (Full Responses) WILD-raw contains the full evaluation responses for 65 language models across 27 benchmarks (109,566 unique items), including conversat