Commonsense Reasoning2019en
WinoGrande
44K Winograd-style problems requiring commonsense reasoning to resolve pronoun references.
Current State of the Art
GPT-4o
OpenAI
87.5
accuracy
Top Models Performance Comparison
Top 3 models ranked by accuracy
Best Score
87.5
Top Model
GPT-4o
Models Compared
3
Score Range
2.2
accuracyPrimary
| # | Model | Score | Paper / Code | Date |
|---|---|---|---|---|
| 1 | GPT-4oAPI OpenAI | 87.5 | Dec 2025 | |
| 2 | Claude 3.5 SonnetAPI Anthropic | 85.4 | Dec 2025 | |
| 3 | Llama 3 70BOpen Source Meta | 85.3 | Dec 2025 |