math benchmark
USAMO25 Leaderboard
USAMO25 is a benchmark based on six proof-based mathematical problems from the 2025 United States of America Mathematical Olympiad.
Updated Sep 5, 2026
Models3
Model coverage3
MetricScore
EvidenceB
USAMO25 Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAN | Score97.60% | Percentile100.00% | Participants3 | EvidenceC | Evaluated |
| Rank02 | ModelXA | Score61.90% | Percentile50.00% | Participants3 | EvidenceC | Evaluated |
| Rank03 | ModelXA | Score37.50% | Percentile0.00% | Participants3 | EvidenceC | Evaluated |
USAMO25 Highlights
The leading models and scores on this benchmark.
USAMO25 Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for USAMO25
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is USAMO25?
What USAMO25 measures and how its scores work.
USAMO25 is a math benchmark consisting of six challenging problems from the 2025 United States of America Mathematical Olympiad.
It measures mathematical problem-solving, formal mathematical reasoning, and proof generation beyond simple numerical computation.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- USAMO25
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about USAMO25.
Which model scores highest on USAMO25?
Claude Mythos Preview is currently ranked first with 97.60%.
What are the top three models on USAMO25?
The current leaders are Claude Mythos Preview (97.60%), Grok-4 Heavy (61.90%), and Grok-4 (37.50%).
Which USAMO25 model has the lowest official input price?
No matched official input price is currently available.
Which models are fastest among USAMO25 results?
The fastest matched records are Grok-4 (100.00 tok/s via xAI).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.