math benchmark
AIME 2024
American Invitational Mathematics Examination 2024, consisting of 30 challenging mathematical reasoning problems from AIME I and AIME II competitions. Each problem requires an integer answer between 0-999 and tests advanced mathematical reasoning across algebra, geometry, combinatorics, and number theory. Used as a benchmark for evaluating mathematical reasoning capabilities in large language models at Olympiad-level difficulty.
Updated Aug 7, 2026
Published models53
Registry coverage53
MetricScore
EvidenceB
AIME 2024 leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
Score distribution
Top published rows on the benchmark's original scale.
AIME 2024 highlights
The top published results on this benchmark's own scale.
What is AIME 2024?
Definition and scoring fields from the benchmark registry.
American Invitational Mathematics Examination 2024, consisting of 30 challenging mathematical reasoning problems from AIME I and AIME II competitions. Each problem requires an integer answer between 0-999 and tests advanced mathematical reasoning across algebra, geometry, combinatorics, and number theory. Used as a benchmark for evaluating mathematical reasoning capabilities in large language models at Olympiad-level difficulty.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- AIME 2024
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- aime-2024|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about AIME 2024.
Which model scores highest on AIME 2024?
Grok-3 Mini is currently ranked first with 95.8%.
What does AIME 2024 measure?
American Invitational Mathematics Examination 2024, consisting of 30 challenging mathematical reasoning problems from AIME I and AIME II competitions. Each problem requires an integer answer between 0-999 and tests advanced mathematical reasoning across algebra, geometry, combinatorics, and number theory. Used as a benchmark for evaluating mathematical reasoning capabilities in large language models at Olympiad-level difficulty.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
53 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is marked as eligible for the current LLMBoard capability methodology.