OpenAI o3-mini (high)

Name: OpenAI o3-mini (high)
Author: OpenAI

Reasoning modelo Minio3

Release date: 2025-01-31Updated: 2025-02-09Views: 1,060

Live demoGitHubHugging FaceCompare

Parameters

No data

Context length

128k

Multilingual

Supported

Reasoning ability

No data

OpenAI o3-mini (high) is an AI model published by OpenAI, released on 2025-01-31, for Reasoning model, and 128k context length, with a 97.90 score on MATH.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

OpenAI o3-mini (high)

Model basics

Reasoning traces

Supported

Thinking modes

Thinking modes not supported

Context length

128k tokens

Max output length

No data

Model type

Reasoning model

Modality (in / out)

Text → Text

Release date

2025-01-31

Model file size

No data

MoE architecture

Total params / Active params

No data / Not applicable

Knowledge cutoff

No data

OpenAI o3-mini (high)

Open source & experience

Code license

Proprietary

Weights license

Proprietary

GitHub repo

N/A

Hugging Face

N/A

Live demo

N/A

OpenAI o3-mini (high)

Official resources

Paper

DataLearnerAI blog

N/A

OpenAI o3-mini (high)

API details

API speed

No data

No public API pricing yet.

OpenAI o3-mini (high)

Benchmark Results

OpenAI o3-mini (high) currently shows benchmark results led by HumanEval (1 / 140, score 97.60), MATH (1 / 42, score 97.90), MATH-500 (9 / 45, score 97.90). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

General Knowledge

2 evaluations

Benchmark / mode

Score

Rank/total

MMLU

Standard Mode

86.90

27 / 124

ARC-AGI-1

Standard Mode

34.50

76 / 92

Coding and Software Engineer

3 evaluations

Benchmark / mode

Score

Rank/total

HumanEval

Standard Mode

97.60

1 / 140

LiveCodeBench

Standard Mode

69.50

58 / 128

SWE-bench Verified

Standard Mode

49.30

97 / 116

Math and Reasoning

5 evaluations

Benchmark / mode

Score

Rank/total

MATH

Standard Mode

97.90

1 / 42

MATH-500

Standard Mode

97.90

9 / 45

AIME 2024

Standard Mode

18 / 62

FrontierMath

High

23 / 60

FrontierMath - Tier 4

High

4.20

40 / 80

General Evaluation

1 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Standard Mode

79.70

150 / 274

Common Sense

1 evaluations

Benchmark / mode

Score

Rank/total

SimpleQA

Standard Mode

13.80

37 / 47

View benchmark analysis Compare with other models

OpenAI o3-mini (high)

Publisher

OpenAI

View publisher details

OpenAI o3-mini (high)

Model Overview

OpenAI o3-mini (high) is an AI model published by OpenAI, released on 2025-01-31, for Reasoning model, and 128k context length, with a 97.90 score on MATH.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.