Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Mathematics benchmark
United States of America Mathematical Olympiad 2026. Every model the catalog carries a published USAMO 2026 value for, ranked by that value.
The premier US mathematical olympiad competition, featuring proof-based problems that require deep mathematical insight and rigorous argumentation at the highest competition level. 3 models in the ModelChoice catalog have a published value.
Each point is a model with a published USAMO 2026 value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
3 models with a published USAMO 2026 value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Mathematical proof construction |
|---|---|---|---|
| 1 | Anthropic | 97.6 | |
| 2 | Anthropic | 96.7 | |
| 3 | MiniMax | 85.71 |
What the benchmark measures and how its value is published, from the source’s own record.
USAMO 2026 (United States of America Mathematical Olympiad 2026) is a mathematics benchmark published by United States of America Mathematical Olympiad. The premier US mathematical olympiad competition, featuring proof-based problems that require deep mathematical insight and rigorous argumentation at the highest competition level. Its evaluation set is described by the source as 6 proof-based problems. The source rates its difficulty as international olympiad level.
Each model's result is published by United States of America Mathematical Olympiad as mathematical proof construction. ModelChoice prints that value exactly as published, and never converts or rescales it. This page ranks the 3 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
Evidence key: Observed
Rows are ordered by the value United States of America Mathematical Olympiad published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.