all the models — AI benchmark observatory
← Benchmarks

DROP

DROP (Discrete Reasoning Over Paragraphs) is a reading comprehension benchmark requiring discrete reasoning over paragraph content. It contains crowdsourced, adversarially-created questions that require resolving references and performing discrete operations like addition, counting, or sorting, demanding comprehensive paragraph understanding beyond paraphrase-and-entity-typing shortcuts.

id drop · max 1 · 30 models reported

#ModelScore
1DeepSeek-V3
DeepSeek · open
0.92