WinoGrande

reasoningPending Human Review

An adversarial winograd schema challenge at scale.

Published: 2019
Score Range: 0-100
Top Score: 84.9

WinoGrande Leaderboard

RankModelProviderScoreParametersReleasedType
1DeepSeek-V3DeepSeek
84.9
671B total, 37B activated2024-12-26Text

About WinoGrande

Methodology

WinoGrande evaluates model performance using a standardized scoring methodology. Scores are reported on a scale of 0 to 100, where higher scores indicate better performance. For detailed information about the scoring system and methodology, please refer to the original paper.

Publication

This benchmark was published in 2019.Website

Related Benchmarks