NOUMENOpen app
NOUMEN

OpenAI · Balanced

OpenAI o3

Added Apr 16, 2025

Compare models

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

Loading models…

Use in the app

OpenAI o3 is a reasoning model for complex analytical, coding, mathematical, and scientific tasks.

  • Reasoning
Input
Text
Output
Text
Reasoning effort
low · medium · high
Discovery tier
Balanced

Pricing

USD per 1M tokens
Input
$2.00
Output
$8.00
Cache read
$1.00

Reference prices as published by the model provider. API example

Specifications

Context window
200K
Max output
100K
Average output (7 days)
205 tokens
Longer than 22% of 468 models

Side by side

OpenAI o3 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 o3OpenAIThis modelLing 3.0 FlashinclusionaiRemove
ProviderOpenAIinclusionai
Discovery tierBalancedEfficient
AddedApr 16, 2025Jul 23, 2026
Limits
Context window200K262.14KBest
Max output100KBest32.77K
Average output205 tokens1.1K tokens
Pricing, USD per 1M tokens
Input$2.00$0.075Best
Output$8.00$0.22Best
Cache read$1.00$0.015Best
Performance
Throughput—279.2 tok/s
Time to first token—1.7 s
Request success (24h)—99.8%
Benchmark indexes
Intelligence Index20.2Best20.1
Coding Index—50.6
Math Index88.3—
Capabilities
ReasoningYesNo
ToolsNoYes
Reasoning effortlow, medium, high—

Public evaluations

Benchmarks

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

  • OpenAI o3
  • Ling 3.0 Flash

Intelligence Index

  • OpenAI o320.2
  • Ling 3.0 Flash20.1

OpenAI o3: Better than 50% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • OpenAI o3: —
    • Ling 3.0 Flash: 50.6

  • Math Index

    Composite of the math evaluations

    • OpenAI o3: 88.3
    • Ling 3.0 Flash: —

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • OpenAI o3: —
    • Ling 3.0 Flash: 3.2%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • OpenAI o3: —
    • Ling 3.0 Flash: 0.6%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • OpenAI o3: —
    • Ling 3.0 Flash: 798 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • OpenAI o3: —
    • Ling 3.0 Flash: 948 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • OpenAI o3: —
    • Ling 3.0 Flash: 5.4%

  • AA-LCRv1.1

    Reasoning across long documents

    • OpenAI o3: 74.7%Top
    • Ling 3.0 Flash: 73.0%

  • MLCR-AA

    Long-context reasoning over medical records

    • OpenAI o3: —
    • Ling 3.0 Flash: 5.0%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • OpenAI o3: 20.1%
    • Ling 3.0 Flash: 23.7%Top

  • GPQA Diamond

    Graduate-level science questions

    • OpenAI o3: 82.7%
    • Ling 3.0 Flash: 85.5%Top

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • OpenAI o3: 85.3%
    • Ling 3.0 Flash: —

  • IFBench

    Following precise output instructions

    • OpenAI o3: 71.4%
    • Ling 3.0 Flash: —

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • OpenAI o3: —
    • Ling 3.0 Flash: 0.0%

  • SciCode

    Scientific computing in Python

    • OpenAI o3: —
    • Ling 3.0 Flash: 42.0%

  • LiveCodeBench

    Recent competitive programming problems

    • OpenAI o3: 80.8%
    • Ling 3.0 Flash: —

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • OpenAI o3: 88.3%
    • Ling 3.0 Flash: —

  • AIME

    Competition mathematics

    • OpenAI o3: 90.3%
    • Ling 3.0 Flash: —

  • MATH-500

    Competition math problems

    • OpenAI o3: 99.2%
    • Ling 3.0 Flash: —

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • OpenAI o3: 37.1%
    • Ling 3.0 Flash: —

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • OpenAI o3: 80.7%
    • Ling 3.0 Flash: —

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • OpenAI o3: 74.7%Top
    • Ling 3.0 Flash: 73.0%

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",
    "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",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

OpenAI

Other OpenAI models, starting with the same family.