Primary evidence
- Measuring Mathematical Problem Solving With the MATH DatasetS1 · Primary research · Paper · 2021-03-05
- MATH dataset repository and evaluation codeS1 · Primary research · Repository
MATH makes competition mathematics a standard language-model benchmark
The benchmark covered algebra, geometry, number theory, probability and other competition topics and provided full solution derivations.
What happened?
The MATH dataset introduced 12,500 challenging competition mathematics problems with step-by-step solutions for training and evaluation.
Why it matters
For several years, progress on MATH served as one of the clearest quantitative signals of LLM mathematical reasoning.
Significance rationale: MATH became a durable benchmark for measuring multi-step competition-level mathematical reasoning and later exposed saturation as reasoning models improved.
Historical context
Earlier developments
Later developments
—
Related milestones
—
Evidence & status at a glance
- Significance
- H2 · Field milestone
- Verification
- Paper released
- Evidence level
- E3 · Inspectable artifact
- AI role
- Computation only
- Formal assurance
- Artifact available
Contribution & verification
- Mathematical novelty
- Tooling only
- Interface
- Informal, Symbolic
- AI contribution
- AI systems are evaluated and trained on the benchmark; the benchmark itself is a human-curated research artifact.
- Human contribution
- Researchers collected problems and solutions, designed the dataset and evaluated scaling behavior.
- Verification
- Paper released · E3 · Inspectable artifact · Artifact available
- Last reviewed
- 2026-09-15
Technical details
- Systems
- math-benchmark
- Organizations
- uc-berkeley
- Problems
- competition-mathematics
- Methods
- benchmarking, dataset-curation
Sources & artifacts
- Measuring Mathematical Problem Solving With the MATH DatasetS1 · Primary research · Paper · accessed 2026-09-10
- MATH dataset repository and evaluation codeS1 · Primary research · Repository · accessed 2026-09-11
- MATH dataset loaders and evaluation codeArtifact · Dataset
Verification history
- 2021-03-05 · Paper released · E2 · Research record
The Chronicle records this event from the cited primary or official source; the status does not imply independent Chronicle verification.
- 2026-09-11 · Paper released · E3 · Inspectable artifact
This corpus refresh added a directly inspectable public artifact maintained by the authors or releasing organization. E3 records artifact-level inspectability and does not imply independent verification of the underlying scientific or mathematical claim.
Corrections
No corrections recorded.