Skip to content
Longterm Wiki has not been actively maintained since May 2026. Some data is still updated occasionally, but please don't rely on this site being current or accurate.
Longterm Wiki

DROP

Reasoning
Wiki pageData
Discrete Reasoning Over Paragraphs — a reading comprehension benchmark requiring numerical reasoning operations such as addition, counting, and sorting over text passages.
Models Tested
4
Best Score
92.2%
Median Score
89.35%
Scoring: accuracy
Introduced: 2019-03
Maintainer: AI2

Leaderboard (4 models)

#ModelDeveloperScore
🥇DeepSeek R1DeepSeek
92.2%
🥈DeepSeek ModelsDeepSeek
91.6
🥉Claude 3.5 SonnetAnthropic
87.1
4GPT-3.5 TurboOpenAI
61.4