NOUMENOpen app
NOUMEN

OpenAI · Frontier

GPT 5.3 Codex

Added Feb 24, 2026

Compare models

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

Loading models…

Use in the app

Coding-focused GPT-5.3 variant with optimized routing.

  • Reasoning
  • Tools
  • Vision
  • Structured output
  • PDF input
Input
Text, Images
Output
Text
Reasoning effort
low · medium · high · xhigh
Discovery tier
Frontier

Pricing

USD per 1M tokens
Input
$1.75
Output
$14.00
Cache read
$0.18

Reference prices as published by the model provider. API example

Specifications

Context window
400K
Max output
128K
Average output (7 days)
281 tokens
Longer than 29% of 465 models

Side by side

GPT 5.3 Codex 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 5.3 CodexOpenAIThis modelMuse Spark 1.1MetaRemove
ProviderOpenAIMeta
Discovery tierFrontierBalanced
AddedFeb 24, 2026Jul 9, 2026
Limits
Context window400K1MBest
Max output128KBest65.54K
Average output281 tokens460 tokens
Pricing, USD per 1M tokens
Input$1.75$1.25Best
Output$14.00$4.25Best
Cache read$0.18$0.15Best
Performance
Request success (24h)98.5%—
Benchmark indexes
Intelligence Index32.533.7Best
Coding Index—71.3
Capabilities
ReasoningYesYes
ToolsYesNo
VisionYesYes
Structured outputYesNo
PDF inputYesNo
Audio inputNoYes
Video inputNoYes
Reasoning effortlow, medium, high, xhighminimal, low, medium, high, xhigh

Public evaluations

Benchmarks

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

  • GPT 5.3 Codex
  • Muse Spark 1.1

Intelligence Index

  • GPT 5.3 Codex32.5
  • Muse Spark 1.133.7

GPT 5.3 Codex tested at xhigh reasoning effort

GPT 5.3 Codex: Better than 76% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • GPT 5.3 Codex: —
    • Muse Spark 1.1: 71.3

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • GPT 5.3 Codex: —
    • Muse Spark 1.1: 38.8%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • GPT 5.3 Codex: —
    • Muse Spark 1.1: 13.7%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • GPT 5.3 Codex: 868 EloTop
    • Muse Spark 1.1: 850 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • GPT 5.3 Codex: —
    • Muse Spark 1.1: 1,211 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • GPT 5.3 Codex: —
    • Muse Spark 1.1: 14.4%

  • AA-LCRv1.1

    Reasoning across long documents

    • GPT 5.3 Codex: 83.3%Top
    • Muse Spark 1.1: 77.7%

  • MLCR-AA

    Long-context reasoning over medical records

    • GPT 5.3 Codex: —
    • Muse Spark 1.1: 7.2%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • GPT 5.3 Codex: 42.5%
    • Muse Spark 1.1: 46.2%Top

  • GPQA Diamond

    Graduate-level science questions

    • GPT 5.3 Codex: 91.5%Top
    • Muse Spark 1.1: 89.8%

  • IFBench

    Following precise output instructions

    • GPT 5.3 Codex: 75.4%
    • Muse Spark 1.1: —

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • GPT 5.3 Codex: —
    • Muse Spark 1.1: 6.1%

  • SciCode

    Scientific computing in Python

    • GPT 5.3 Codex: —
    • Muse Spark 1.1: 58.8%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • GPT 5.3 Codex: 53.0%
    • Muse Spark 1.1: —

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • GPT 5.3 Codex: 86.0%
    • Muse Spark 1.1: —

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • GPT 5.3 Codex: 83.3%Top
    • Muse Spark 1.1: 77.7%

Scores from Artificial Analysis, updated Oct 26, 2026. GPT 5.3 Codex was tested at xhigh 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
7.7%
About $1.63 per 1M input tokens with caching
Request success (24h)
98.5%
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 97.4%
  • 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-5.3-codex",
    "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-5.3-codex",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

OpenAI

Other OpenAI models, starting with the same family.