math benchmark
USAMO 2026 evaluates models on six problems from the 2026 United States of America Mathematical Olympiad using rigorous proof-based reasoning.
Updated Sep 5, 2026
Higher score ranks better on this benchmark.
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMI | Score36.00 points | Percentile100.00% | Participants3 | EvidenceC | Evaluated |
| Rank02 | ModelAN | Score33.39 points | Percentile50.00% | Participants3 | EvidenceC | Evaluated |
| Rank03 | ModelTE | Score30.24 points | Percentile0.00% | Participants3 | EvidenceC | Evaluated |
The leading models and scores on this benchmark.
A closer view of the leading scores on this benchmark.
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What USAMO 2026 measures and how its scores work.
USAMO 2026 is a math benchmark based on the six problems from the 2026 United States of America Mathematical Olympiad.
It measures proof-based reasoning with the Score metric in points, graded against human expert rubrics by dual strong judge models; the minimum of the two scores is used as the final score, with a maximum of 42 points.
Scores are shown in points. This benchmark is not independently verified and has an evidence level of B.
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
Common questions about USAMO 2026.
MiniMax M3 is currently ranked first with 36.00 points.
The current leaders are MiniMax M3 (36.00 points), Claude Sonnet 5 (33.39 points), and Hy3 (30.24 points).
MiniMax M3 has the lowest matched official input price at $0.30 input / $1.2 output per 1M tokens.
The fastest matched records are Claude Sonnet 5 (42.00 tok/s via Anthropic) and MiniMax M3 (6.61 tok/s via MiniMax).
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.
It measures proof-based reasoning with the Score metric in points, graded against human expert rubrics by dual strong judge models; the minimum of the two scores is used as the final score, with a maximum of 42 points.
Yes. Higher values rank better for this benchmark.
3 model results are currently shown.
No. This benchmark is shown for reference but does not contribute to the overall score.
Ranking basisThis usamo 2026 AI model leaderboard uses descending score in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
Selection summary
MiniMax M3 currently leads USAMO 2026 with 36.00 points. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price, and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.