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.
DeepSeek-V3 from DeepSeek currently leads the DROP leaderboard with a score of 0.916 across 29 evaluated AI models.
DeepSeek-V3 leads with 91.6%, followed by 
Claude 3.5 Sonnet at 87.1% and Claude 3.5 Sonnet at 87.1%.
Progress Over Time
Interactive timeline showing model performance evolution on DROP
DROP Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | DeepSeek | 671B | — | — | ||
| 2 | Anthropic | — | — | — | ||
| 2 | Anthropic | — | — | — | ||
| 4 |  OpenAI | — | 128K | $10.00 / $30.00 | ||
| 5 |  Amazon | — | — | — | ||
| 6 | 405B | — | — | |||
| 7 | OpenAI | — | 128K | $2.50 / $10.00 | ||
| 8 | Anthropic | — | — | — | ||
| 8 | Anthropic | — | — | — | ||
| 10 | OpenAI | — | — | — | ||
| 11 | Amazon | — | — | — | ||
| 12 | OpenAI | — | — | — | ||
| 13 | 70B | — | — | |||
| 14 | Amazon | — | — | — | ||
| 15 |  Meituan | 560B | 128K | $0.30 / $1.20 | ||
| 16 | Anthropic | — | — | — | ||
| 17 | Anthropic | — | — | — | ||
| 18 |  Microsoft | 15B | — | — | ||
| 19 |  Google | — | — | — | ||
| 20 | OpenAI | — | 16K | $0.50 / $1.50 | ||
| 21 | 2B | — | — | |||
| 21 | Google | 8B | — | — | ||
| 23 | 8B | — | — | |||
| 24 | 8B | — | — | |||
| 25 | Google | 8B | — | — | ||
| 25 | 2B | — | — | |||
| 27 | 7B | — | — | |||
| 28 | 8B | — | — | |||
| 29 |  Baidu | 21B | — | — |
FAQ
Common questions about DROP.
More evaluations to explore
Related benchmarks in the same category
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions