Evaluation & Benchmarks · 2021

GSM8K / MATH (mathematical reasoning)

Karl Cobbe, Vineet Kosaraju, John Schulman, Dan Hendrycks, Jacob Steinhardt

Released the MATH dataset of competition mathematics problems with full step-by-step solutions, providing a hard benchmark that exposed how weak language models were at multi-step mathematical reasoning.

Editorial record

Plain-language summary

MATH contains 12,500 competition-level problems, each with a worked solution, spanning subjects like algebra, geometry, and number theory at varying difficulty. Because answers require multi-step derivations rather than lookup, early large models scored very low, making it a clear measure of reasoning progress. It is often paired with GSM8K, a grade-school word-problem set, and together they became standard yardsticks for tracking improvements in chain-of-thought and mathematical reasoning.

Knowledge graph

Relationships

Antecedents

Source record

Provenance

Record ID
P-442
Record created
2026-07-13
Last reviewed
2026-07-14
Record version
2

Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.