OpenAI: o3 Mini High

OpenAI: o3 Mini High

openai · Released Feb 12, 2025 Professional
Intelligence #10 / 565
82.0 Our Score
Speed #39 / 262
196.1 tokens / sec
Input #438 / 565
$1.10 per 1M tokens
Output #446 / 565
$4.40 per 1M tokens
Context #192 / 565
200,000 tokens

Analysis Summary

OpenAI: o3 Mini High sits in the Professional tier on our leaderboard, ranked #10 of 565 published models on overall intelligence. At $1.10 input and $4.40 output per 1M tokens, it is among the most expensive on the market. It offers a generous context window for extended reasoning and code review and supports tool use, function calling, and reasoning.

Editorial notes

OpenAI o3 Mini High delivers top-tier reasoning and coding benchmarks with strong GPQA and HLE scores, tool use, and a 200K context; a reliable high-effort reasoning option from OpenAI at moderate cost.

Assessed May 31, 2026

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence4.3Technical3.2Value7Content6
Intelligence 4.3/10
Technical 3.2/10
Content 6/10
Value 7/10

How OpenAI: o3 Mini High compares

OpenAI: o3 Mini High ranks #141 of 370 AI models we track for overall intelligence, #158 of 307 for coding, #180 of 282 for agentic tasks. Its 200K-token context window is larger than 66% of the models we list. At $1.10 per million input tokens it is cheaper than 22% of comparable models.

About OpenAI: o3 Mini High

OpenAI o3-mini-high is the same model as o3-mini with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and..

Capabilities

Tool Use Function Calling

Performance Indices

Source: Artificial Analysis

25.2 Intelligence Index
17.3 Coding Index
18.7 Agentic Index

Benchmark Scores

Intelligence

GPQA Diamond 77.3% Graduate-level scientific reasoning
HLE 12.3% Humanity's Last Exam
MMLU Pro 80.2% Multi-task language understanding
MATH 500 98.5% Mathematical problem-solving
AIME 86% Competition mathematics
SciCode 39.8% Scientific computing

Technical

LiveCodeBench 73.4% Live coding evaluation
TerminalBench Hard 6.1% Agentic terminal tasks
τ²-Bench 31.3% Conversational agent benchmark

Content

IFBench 67.1% Instruction following
LCR 39.3% Long-context reasoning

Benchmark data from Artificial Analysis and Hugging Face

How does OpenAI: o3 Mini High stack up?

Compare side-by-side with other professional models.

Compare Models

Model Information

OpenRouter ID openai/o3-mini-high
Provideropenai
Model Familyo3
Release Date February 12, 2025
Context Length200,000 tokens
Max Completion100,000 tokens
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $1.10 $0.001100
Output $4.40 $0.004400

Live Performance

Live endpoint metrics, refreshed every 30 minutes.

273ms
Best Latency (TTFT)
13 tok/s
Best Throughput
0/1
Active Endpoints
Available via: OpenAI

Leaderboard Categories

Frequently asked questions about OpenAI: o3 Mini High

How much does OpenAI: o3 Mini High cost?

OpenAI: o3 Mini High costs $1.10 per million input tokens and $4.40 per million output tokens.

What is the context window of OpenAI: o3 Mini High?

OpenAI: o3 Mini High has a context window of 200,000 tokens (200K).

Is OpenAI: o3 Mini High good for coding?

On our coding benchmark index, OpenAI: o3 Mini High ranks #158 of 307 models, placing it in the broader range of the field for code generation and debugging.

What can OpenAI: o3 Mini High do?

OpenAI: o3 Mini High supports tool use and function calling.

Who created OpenAI: o3 Mini High?

OpenAI: o3 Mini High is developed by OpenAI and was released on February 12, 2025.