NOUMENOpen app
NOUMEN

OpenAI · Efficient

OpenAI o3-mini (High)

Added Jan 1, 2024

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

OpenAI's o3-mini reasoning model with reasoning effort set to high.

  • Reasoning
  • Tools
  • Structured output
Input
Text
Output
Text
Reasoning effort
low · medium · high
Discovery tier
Efficient

Pricing

USD per 1M tokens
Input
$1.10
Output
$4.40
Cache read
$0.55

Reference prices as published by the model provider. API example

Specifications

Context window
200K
Max output
100K

Side by side

OpenAI o3-mini (High) compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

OpenAI o3-mini (High)OpenAIThis modelGPT 6 SolOpenAIRemove
ProviderOpenAIOpenAI
Discovery tierEfficientFrontier
AddedJan 1, 2024Sep 22, 2026
Limits
Context window200K1.05MBest
Max output100K128KBest
Average output—315 tokens
Pricing, USD per 1M tokens
Input$1.10Best$2.00
Output$4.40Best$10.00
Cache read$0.55$0.20Best
Cache write—$2.50
Performance
Throughput—212.1 tok/s
Time to first token—3.1 s
Request success (24h)—100.0%
Benchmark indexes
Intelligence Index12.539.8Best
Capabilities
ReasoningYesYes
ToolsYesYes
VisionNoYes
Structured outputYesYes
PDF inputNoYes
Reasoning effortlow, medium, highnone, low, medium, high, xhigh, max

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • OpenAI o3-mini (High)
  • GPT 6 Sol

Intelligence Index

  • OpenAI o3-mini (High)12.5
  • GPT 6 Sol39.8

OpenAI o3-mini (High): Better than 27% of 326 scored models

3.8Catalog models by score55.1

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • OpenAI o3-mini (High): —
    • GPT 6 Sol: 58.0%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • OpenAI o3-mini (High): —
    • GPT 6 Sol: 28.2%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • OpenAI o3-mini (High): —
    • GPT 6 Sol: 1,148 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • OpenAI o3-mini (High): —
    • GPT 6 Sol: 1,346 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • OpenAI o3-mini (High): —
    • GPT 6 Sol: 23.8%

  • AA-LCRv1.1

    Reasoning across long documents

    • OpenAI o3-mini (High): —
    • GPT 6 Sol: 82.3%

  • MLCR-AA

    Long-context reasoning over medical records

    • OpenAI o3-mini (High): —
    • GPT 6 Sol: 28.9%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • OpenAI o3-mini (High): 7.9%
    • GPT 6 Sol: 41.0%Top

  • GPQA Diamond

    Graduate-level science questions

    • OpenAI o3-mini (High): 74.8%
    • GPT 6 Sol: —

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • OpenAI o3-mini (High): 79.1%
    • GPT 6 Sol: —

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • OpenAI o3-mini (High): —
    • GPT 6 Sol: 18.7%

  • SciCode

    Scientific computing in Python

    • OpenAI o3-mini (High): —
    • GPT 6 Sol: 53.8%

  • LiveCodeBench

    Recent competitive programming problems

    • OpenAI o3-mini (High): 71.7%
    • GPT 6 Sol: —

Math

  • AIME

    Competition mathematics

    • OpenAI o3-mini (High): 77.0%
    • GPT 6 Sol: —

  • MATH-500

    Competition math problems

    • OpenAI o3-mini (High): 97.3%
    • GPT 6 Sol: —

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • OpenAI o3-mini (High): 6.8%
    • GPT 6 Sol: —

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • OpenAI o3-mini (High): 28.7%
    • GPT 6 Sol: —

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • OpenAI o3-mini (High): —
    • GPT 6 Sol: 82.3%

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/o3-mini-high",
    "reasoning_effort": "medium",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="openai/o3-mini-high",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

OpenAI

Other OpenAI models, starting with the same family.