🏆 MathBench Leaderboard 🏆

MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark [ACL2024 findings]

description Paper code Code

📝 Notes

  1. Models labeled with 🌍 are Closed-source models, while others are Open-sourced.
  2. Models labeled with 🧮 are Mathematics-Specialization models, while others are normal Chat models.
  3. Feel free to file a request to add your models on our leaderboard.