# O1 ProHigh

> Source: Benchize (https://benchize.com) — https://benchize.com/models/o1-pro-high. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/o1-pro-high.

OpenAI

Canonical URL: https://benchize.com/models/o1-pro-high
Last updated: Thu, 22 Oct 2026 07:32:33 GMT

Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations.

OpenAI

## Benchmarks

| Benchmark | Score | ± | Rank | Cost |  |
| --- | --- | --- | --- | --- | --- |
| [USAMO 2025](https://benchize.com/benchmarks/matharena%3Ausamo--usamo_2025.md) | 2.83% | 95% CI -3.8–9.46% | 4 / 5 | 9.51usd per problem |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 2.83 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 9.51 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition usamo--usamo_2025 predicted false Reasoning effort high sourceModelName o1-pro (high) sourceModelVersion openai/o1-pro thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: -3.8–9.46% confidenceInterval95 6.63 problems 6 ### Source [Original source](https://matharena.ai/competition_tables/usamo--usamo_2025) Source matharena Original model label o1-pro (high) Source version usamo--usamo_2025 Observed 2026-10-22T05:30:14.324Z Evidence SHA-256 `3daa94d7a67853824c18907dcfe72cfcadb00866a149a4de2c63a823b295e99f` Source locator `/table/rows/8` |  |  |  |  |  |

---
Cite as: O1 ProHigh — Benchize, https://benchize.com/models/o1-pro-high (retrieved 2026-10-22)