NOUMENOpen app
NOUMEN

OpenAI · Efficient

GPT 5 Mini

Added Aug 7, 2025

Compare models

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

Loading models…

Use in the app

A lightweight version of GPT-5 for cost-sensitive applications. Balances advanced capabilities with efficient resource usage.

  • Reasoning
  • Vision
Input
Text, Images
Output
Text
Reasoning effort
minimal · low · medium · high
Discovery tier
Efficient

Pricing

USD per 1M tokens
Input
$0.25
Output
$2.00
Cache read
$0.025

Reference prices as published by the model provider. API example

Specifications

Context window
400K
Max output
128K
Average output (7 days)
891 tokens
Longer than 67% of 465 models

Side by side

GPT 5 Mini 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…

GPT 5 MiniOpenAIThis modelGPT 4.1 MiniOpenAIRemove
ProviderOpenAIOpenAI
Discovery tierEfficientEfficient
AddedAug 7, 2025Sep 10, 2025
Limits
Context window400K1.05MBest
Max output128KBest32.77K
Average output891 tokens19 tokens
Pricing, USD per 1M tokens
Input$0.25Best$0.40
Output$2.00$1.60Best
Cache read$0.025Best$0.10
Performance
Request success (24h)100.0%100.0%
Benchmark indexes
Intelligence Index16.8Best10.2
Coding Index15.620.2Best
Math Index90.7Best46.3
Capabilities
ReasoningYesNo
VisionYesYes
Reasoning effortminimal, low, medium, high—

Public evaluations

Benchmarks

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

  • GPT 5 Mini
  • GPT 4.1 Mini

Intelligence Index

  • GPT 5 Mini16.8
  • GPT 4.1 Mini10.2

GPT 5 Mini tested at high reasoning effort

GPT 5 Mini: Better than 45% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • GPT 5 Mini: 15.6
    • GPT 4.1 Mini: 20.2Top

  • Math Index

    Composite of the math evaluations

    • GPT 5 Mini: 90.7Top
    • GPT 4.1 Mini: 46.3

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • GPT 5 Mini: 6.5%
    • GPT 4.1 Mini: —

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • GPT 5 Mini: 0.9%
    • GPT 4.1 Mini: —

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • GPT 5 Mini: 428 Elo
    • GPT 4.1 Mini: —

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • GPT 5 Mini: 766 EloTop
    • GPT 4.1 Mini: 270 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • GPT 5 Mini: 8.4%
    • GPT 4.1 Mini: —

  • AA-LCRv1.1

    Reasoning across long documents

    • GPT 5 Mini: 72.3%Top
    • GPT 4.1 Mini: 44.0%

  • MLCR-AA

    Long-context reasoning over medical records

    • GPT 5 Mini: 8.9%
    • GPT 4.1 Mini: —

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • GPT 5 Mini: 21.5%Top
    • GPT 4.1 Mini: 5.0%

  • GPQA Diamond

    Graduate-level science questions

    • GPT 5 Mini: 82.8%Top
    • GPT 4.1 Mini: 66.4%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • GPT 5 Mini: 83.7%Top
    • GPT 4.1 Mini: 78.1%

  • IFBench

    Following precise output instructions

    • GPT 5 Mini: 75.4%Top
    • GPT 4.1 Mini: 38.3%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • GPT 5 Mini: 0.0%
    • GPT 4.1 Mini: —

  • SciCode

    Scientific computing in Python

    • GPT 5 Mini: 39.0%
    • GPT 4.1 Mini: —

  • LiveCodeBench

    Recent competitive programming problems

    • GPT 5 Mini: 83.8%Top
    • GPT 4.1 Mini: 48.3%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • GPT 5 Mini: 90.7%Top
    • GPT 4.1 Mini: 46.3%

  • AIME

    Competition mathematics

    • GPT 5 Mini: —
    • GPT 4.1 Mini: 43.0%

  • MATH-500

    Competition math problems

    • GPT 5 Mini: —
    • GPT 4.1 Mini: 92.5%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • GPT 5 Mini: 33.3%Top
    • GPT 4.1 Mini: 7.6%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • GPT 5 Mini: 68.4%Top
    • GPT 4.1 Mini: 52.9%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • GPT 5 Mini: 72.3%Top
    • GPT 4.1 Mini: 44.0%

Scores from Artificial Analysis, updated Oct 26, 2026. GPT 5 Mini was tested at high reasoning effort; compare scores measured at the same effort.Artificial Analysis

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Prompt cache hits
22.1%
About $0.20 per 1M input tokens with caching
Request success (24h)
100.0%
Reliable

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Hourly request success · last 72 hoursLowest hour 100.0%
  • Healthy (98% or more)
  • Degraded (90–98%)
  • Down (under 90%)
  • No requests

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/gpt-5-mini",
    "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/gpt-5-mini",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

OpenAI

Other OpenAI models, starting with the same family.