# MATH

> MATH is a benchmark of 12,500 competition mathematics problems, spanning seven subjects and five difficulty levels, each with a full step-by-step solution.

- Identifier: PTL-0198
- Category: Benchmarks
- Canonical URL: https://protologue.com/t/math-benchmark/
- Also known as: MATH dataset, MATH-500
- Introduced: 2021

## Description

It is much harder than grade-school arithmetic and was long a key measure of mathematical reasoning. A 500-problem subset, MATH-500, created for research on process supervision, is the version most often reported today.

## Broader terms

- [Benchmark](https://protologue.com/t/benchmark/)

## Related terms

- [GSM8K](https://protologue.com/t/gsm8k/)
- [AIME](https://protologue.com/t/aime/)
- [Process Reward Model](https://protologue.com/t/process-reward-model/)

## Sources

- Hendrycks et al. (2021). Measuring Mathematical Problem Solving With the MATH Dataset. https://arxiv.org/abs/2103.03874
- Lightman et al. (2023). Let's Verify Step by Step. https://arxiv.org/abs/2305.20050

## Cite this entry

Protologue. (2026). MATH. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0198). https://protologue.com/t/math-benchmark/

License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)