Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models

TL;DR

This paper introduces Omni-MATH, a comprehensive benchmark with 4428 Olympiad-level math problems designed to evaluate large language models' reasoning capabilities, revealing current models' struggles with high-level mathematical problems.

Contribution

The paper presents a new, challenging Olympiad-level math benchmark with extensive categorization and difficulty levels, filling gaps left by existing datasets.

Findings

Even advanced models perform poorly on Olympiad problems.

Models achieve around 50-60% accuracy, indicating room for improvement.

The benchmark enables detailed assessment of mathematical reasoning in LLMs.

Abstract

Recent advancements in large language models (LLMs) have led to significant breakthroughs in mathematical reasoning capabilities. However, existing benchmarks like GSM8K or MATH are now being solved with high accuracy (e.g., OpenAI o1 achieves 94.8\% on MATH dataset), indicating their inadequacy for truly challenging these models. To bridge this gap, we propose a comprehensive and challenging benchmark specifically designed to assess LLMs' mathematical reasoning at the Olympiad level. Unlike existing Olympiad-related benchmarks, our dataset focuses exclusively on mathematics and comprises a vast collection of 4428 competition-level problems with rigorous human annotation. These problems are meticulously categorized into over 33 sub-domains and span more than 10 distinct difficulty levels, enabling a holistic assessment of model performance in Olympiad-mathematical reasoning. Furthermore, we conducted an in-depth analysis based on this benchmark. Our experimental results show that even the most advanced models, OpenAI o1-mini and OpenAI o1-preview, struggle with highly challenging Olympiad-level problems, with 60.54\% and 52.55\% accuracy, highlighting significant challenges in Olympiad-level mathematical reasoning.