math benchmark
AIME
American Invitational Mathematics Examination (AIME) benchmark for evaluating mathematical reasoning capabilities of large language models. Contains 30 challenging mathematical problems from AIME 2024 competition that require multi-step reasoning and advanced mathematical insight. Each problem has an integer answer between 000-999.
Updated Aug 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
AIME leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | MI | 57.5% | 100.0% | 2 | C | |
| 2 | XI | 37.3% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
AIME highlights
The top published results on this benchmark's own scale.
What is AIME?
Definition and scoring fields from the benchmark registry.
American Invitational Mathematics Examination (AIME) benchmark for evaluating mathematical reasoning capabilities of large language models. Contains 30 challenging mathematical problems from AIME 2024 competition that require multi-step reasoning and advanced mathematical insight. Each problem has an integer answer between 000-999.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- AIME
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- aime|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about AIME.
Which model scores highest on AIME?
Phi 4 Mini Reasoning is currently ranked first with 57.5%.
What does AIME measure?
American Invitational Mathematics Examination (AIME) benchmark for evaluating mathematical reasoning capabilities of large language models. Contains 30 challenging mathematical problems from AIME 2024 competition that require multi-step reasoning and advanced mathematical insight. Each problem has an integer answer between 000-999.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.