math benchmark
AIME 2026
All 30 problems from the 2026 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Updated Aug 7, 2026
Published models17
Registry coverage17
MetricScore
EvidenceB
AIME 2026 leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | ZA | 99.2% | 100.0% | 17 | C | |
| 2 | MA | 96.4% | 93.8% | 17 | C | |
| 3 | ZA | 95.3% | 87.5% | 17 | C | |
| 4 | AC | 95.3% | 81.3% | 17 | C | |
| 5 | MI | 94.5% | 75.0% | 17 | C | |
| 6 | BY | 94.2% | 68.8% | 17 | C | |
| 7 | AC | 94.1% | 62.5% | 17 | C | |
| 8 | AC | 92.7% | 56.3% | 17 | C | |
| 9 | MI | 92.5% | 50.0% | 17 | C | |
| 10 | AC | 91.3% | 43.8% | 17 | C | |
| 11 | GO | 89.2% | 37.5% | 17 | C | |
| 12 | GO | 88.3% | 31.3% | 17 | C | |
| 13 | BY | 88.3% | 25.0% | 17 | C | |
| 14 | GO | 77.5% | 18.8% | 17 | C | |
| 15 | GO | 69.1% | 12.5% | 17 | C | |
| 16 | GO | 42.5% | 6.3% | 17 | C | |
| 17 | GO | 37.5% | 0.0% | 17 | C |
Score distribution
Top published rows on the benchmark's original scale.
AIME 2026 highlights
The top published results on this benchmark's own scale.
What is AIME 2026?
Definition and scoring fields from the benchmark registry.
All 30 problems from the 2026 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- AIME 2026
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- aime-2026|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about AIME 2026.
Which model scores highest on AIME 2026?
GLM-5.2 is currently ranked first with 99.2%.
What does AIME 2026 measure?
All 30 problems from the 2026 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
17 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.