ModelRefs / DROP Leaderboard — AI Model Scores
DROP Leaderboard — AI Model Scores
Discrete reasoning over paragraphs — math/counting/sorting inside reading comp. Current leaders, methodology, and citation sources for DROP.
Overview
Discrete reasoning over paragraphs — math/counting/sorting inside reading comp.
How it is measured: F1 over numeric & span answers.
How this benchmark is scored
| Category | reasoning |
|---|---|
| Maximum score | 100 F1 |
| Direction | Higher is better |
Primary source: https://arxiv.org/abs/1903.00161
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to DROP Leaderboard — AI Model Scores.