English

Mathador-LM: A Dynamic Benchmark for Mathematical Reasoning on Large Language Models

Computation and Language 2024-10-16 v3 Artificial Intelligence Machine Learning

Abstract

We introduce Mathador-LM, a new benchmark for evaluating the mathematical reasoning on large language models (LLMs), combining ruleset interpretation, planning, and problem-solving. This benchmark is inspired by the Mathador game, where the objective is to reach a target number using basic arithmetic operations on a given set of base numbers, following a simple set of rules. We show that, across leading LLMs, we obtain stable average performance while generating benchmark instances \emph{dynamically}, following a target difficulty level. Thus, our benchmark alleviates concerns about test-set leakage into training data, an issue that often undermines popular benchmarks. Additionally, we conduct a comprehensive evaluation of both open and closed-source state-of-the-art LLMs on Mathador-LM. Our findings reveal that contemporary models struggle with Mathador-LM, scoring significantly lower than average 3rd graders. This stands in stark contrast to their strong performance on popular mathematical reasoning benchmarks. The implementation of Mathador-LM benchmark is available at \href{https://github.com/IST-DASLab/Mathador-LM}{github.com/IST-DASLab/Mathador-LM}.

Keywords

Cite

@article{arxiv.2406.12572,
  title  = {Mathador-LM: A Dynamic Benchmark for Mathematical Reasoning on Large Language Models},
  author = {Eldar Kurtic and Amir Moeini and Dan Alistarh},
  journal= {arXiv preprint arXiv:2406.12572},
  year   = {2024}
}

Comments

EMNLP 2024

R2 v1 2026-06-28T17:10:19.859Z