Arithmetic Reasoning2021en
Simple Variations on Arithmetic Math Word Problems
1,000 elementary-level math word problems testing robustness of arithmetic reasoning.
Current State of the Art
GPT-4o
OpenAI
93.7
accuracy
Top Models Performance Comparison
Top 3 models ranked by accuracy
Best Score
93.7
Top Model
GPT-4o
Models Compared
3
Score Range
4.2
accuracyPrimary
| # | Model | Score | Paper / Code | Date |
|---|---|---|---|---|
| 1 | GPT-4oAPI OpenAI | 93.7 | Dec 2025 | |
| 2 | Claude 3.5 SonnetAPI Anthropic | 91.2 | Dec 2025 | |
| 3 | Llama 3 70BOpen Source Meta | 89.5 | Dec 2025 |