Evaluation & Benchmarks · 2021
GSM8K / MATH (mathematical reasoning)
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
Provides evaluation forEvidence: Direct
Solving Quantitative Reasoning Problems with Language Models (Minerva)
Minerva is evaluated on the MATH benchmark
P-522
Source record
Provenance
- Record ID
- P-442
- Record created
- 2026-07-13
- Last reviewed
- 2026-07-14
- Record version
- 2
- https://arxiv.org/abs/2103.03874
- arXiv:2103.03874
Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.