NOUMENOpen app
NOUMEN

OpenAI · Frontier

GPT 5.2 Codex

Added Jan 14, 2026

Compare models

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

Loading models…

Use in the app

Coding-focused GPT-5.2 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)
41 tokens
Longer than 3% of 465 models

Side by side

GPT 5.2 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 5.2 CodexOpenAIThis modelMiniMax M3MiniMaxRemove
ProviderOpenAIMiniMax
Discovery tierFrontierOpen weights
AddedJan 14, 2026Jun 1, 2026
Limits
Context window400K512KBest
Max output128KBest80K
Average output41 tokens491 tokens
Pricing, USD per 1M tokens
Input$1.75$0.23Best
Output$14.00$0.96Best
Cache read$0.18$0.05Best
Performance
Throughput—87.7 tok/s
Time to first token—1.8 s
Request success (24h)—99.9%
Benchmark indexes
Intelligence Index28.529.2Best
Coding Index—58.6
Capabilities
ReasoningYesNo
ToolsYesYes
VisionYesYes
Structured outputYesYes
PDF inputYesNo
Reasoning effortlow, medium, high, xhigh—

Public evaluations

Benchmarks

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

  • GPT 5.2 Codex
  • MiniMax M3

Intelligence Index

  • GPT 5.2 Codex28.5
  • MiniMax M329.2

GPT 5.2 Codex tested at xhigh reasoning effort

GPT 5.2 Codex: Better than 70% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • GPT 5.2 Codex: —
    • MiniMax M3: 58.6

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • GPT 5.2 Codex: —
    • MiniMax M3: 21.3%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • GPT 5.2 Codex: —
    • MiniMax M3: 4.4%

  • Harvey LAB-AAv1.1

    Legal tasks passed in full, with no material hallucination

    • GPT 5.2 Codex: —
    • MiniMax M3: 0.0%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • GPT 5.2 Codex: —
    • MiniMax M3: 1,089 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • GPT 5.2 Codex: —
    • MiniMax M3: 1,243 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • GPT 5.2 Codex: —
    • MiniMax M3: 9.8%

  • AA-LCRv1.1

    Reasoning across long documents

    • GPT 5.2 Codex: 82.3%
    • MiniMax M3: 83.0%Top

  • MLCR-AA

    Long-context reasoning over medical records

    • GPT 5.2 Codex: —
    • MiniMax M3: 4.4%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • GPT 5.2 Codex: 35.7%
    • MiniMax M3: 39.0%Top

  • GPQA Diamond

    Graduate-level science questions

    • GPT 5.2 Codex: 89.9%
    • MiniMax M3: 92.9%Top

  • IFBench

    Following precise output instructions

    • GPT 5.2 Codex: 77.6%
    • MiniMax M3: 82.9%Top

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • GPT 5.2 Codex: —
    • MiniMax M3: 2.0%

  • SciCode

    Scientific computing in Python

    • GPT 5.2 Codex: —
    • MiniMax M3: 47.1%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • GPT 5.2 Codex: 37.1%
    • MiniMax M3: 42.4%Top

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • GPT 5.2 Codex: 92.1%Top
    • MiniMax M3: 88.9%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • GPT 5.2 Codex: 82.3%
    • MiniMax M3: 83.0%Top

Scores from Artificial Analysis, updated Oct 26, 2026. GPT 5.2 Codex was tested at xhigh reasoning effort; compare scores measured at the same effort.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/gpt-5.2-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-5.2-codex",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

OpenAI

Other OpenAI models, starting with the same family.