Mathematical Reasoning on G Hard
0.776AccuracyGPT-4
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4Protocol=PAL, Setting=Tool manipulation2024.05 | 0.776 | |
| ChatGPTProtocol=PAL, Setting=Tool manipulation2024.05 | 0.676 | |
| JiuZhang3.0-7BSetting=Tool manipulation, Model Size=7B2024.05 | 0.649 | |
| JiuZhang3.0-8BSetting=Tool manipulation, Model Size=8B2024.05 | 0.644 | |
| OpenMath-Mistral-7BSetting=Tool manipulation, Model Size=7B, Backbone=Mistral2024.05 | 0.637 | |
| Rho-1-Math-7B-CodeSetting=Tool manipulation, Model Size=7B2024.05 | 0.631 | |
| TORA-7B-CodeSetting=Tool manipulation, Model Size=7B2024.05 | 0.56 | |
| CodeLLamaSetting=Tool manipulation2024.05 | 0.336 |