AIME
matharena.ai- Category
- Developer Tools
- Listed in
- #49 Find AI benchmarks
- Type
- TOOL
- Date
About
The American Invitational Mathematics Examination: 15 high-school olympiad qualifier problems per paper with integer answers from 0 to 999. Each year's paper is a separate edition, and newer papers resist training-data contamination, so compare scores from the same year, sample count, and sampling settings.
Why it made the leaderboard
Compare the task, benchmark version, harness, and grading method before using model scores to choose a model.
Tags
benchmarkevaluation
Comments (0)
No comments yet
Editorially curated, with community endorsements as a secondary signal. Corrections welcome.