Commonsense Reasoning2019en
CommonsenseQA
12,247 multiple choice questions requiring commonsense reasoning about everyday concepts.
Current State of the Art
GPT-4o
OpenAI
85.4
accuracy
Top Models Performance Comparison
Top 3 models ranked by accuracy
Best Score
85.4
Top Model
GPT-4o
Models Compared
3
Score Range
4.5
accuracyPrimary
| # | Model | Score | Paper / Code | Date |
|---|---|---|---|---|
| 1 | GPT-4oAPI OpenAI | 85.4 | Dec 2025 | |
| 2 | Claude 3.5 SonnetAPI Anthropic | 83.2 | Dec 2025 | |
| 3 | Llama 3 70BOpen Source Meta | 80.9 | Dec 2025 |