← all datasets

DROP

Canonical
3papers using it
8,342HF downloads
68HF likes
2025first seen

Dataset Card for "drop" Dataset Summary DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs. . DROP is a crowdsourced, adversarially-created, 96k-question benchmark, in which a system must resolve references in a question, perhaps to multiple input positions, and perform discrete operat

Papers using DROP (3)

DROP β€” datasets β€” llm-papers