This project evaluates the mathematical capabilities of Large Language Models (LLMs) and examines how providing hints in prompts affects their performance.

This tool generates mathematical problems, presents them to LLMs with and without hints, and analyzes the responses to assess:

• The baseline mathematical ability of LLMs
• How hint-enhanced prompts impact the accuracy and approach of LLM solutions

Contributions are welcome! Please read our Contributing Guide for more information.

This project is licensed under the - see the LICENSE file for details.