OpenAI · Frontier
GPT 5.2 Codex
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.
| GPT 5.2 CodexOpenAIThis model | Gemini Pro LatestGoogleRemove | |
|---|---|---|
| Provider | OpenAI | |
| Discovery tier | Frontier | Frontier |
| Added | Jan 14, 2026 | Mar 29, 2026 |
| Limits | ||
| Context window | 400K | 1.05MBest |
| Max output | 128KBest | 65.54K |
| Average output | 41 tokens | — |
| Pricing, USD per 1M tokens | ||
| Input | $1.75Best | $2.00 |
| Output | $14.00 | $12.00Best |
| Cache read | $0.18Best | $0.20 |
| Cache write | — | $0.38 |
| Performance | ||
| Throughput | — | 36.1 tok/s |
| Time to first token | — | 8.7 s |
| Request success (24h) | — | 100.0% |
| Benchmark indexes | ||
| Intelligence Index | 28.5 | 29.7Best |
| Coding Index | — | 68.8 |
| Capabilities | ||
| Reasoning | Yes | Yes |
| Tools | Yes | Yes |
| Vision | Yes | Yes |
| Structured output | Yes | Yes |
| PDF input | Yes | No |
| Audio input | No | Yes |
| Video input | No | Yes |
| Reasoning effort | low, 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
- Gemini Pro Latest
Intelligence Index
- GPT 5.2 Codex28.5
- Gemini Pro Latest29.7
GPT 5.2 Codex tested at xhigh reasoning effort
GPT 5.2 Codex: Better than 70% of 326 scored models
Indexes
Coding Index
Composite of the coding evaluations
- GPT 5.2 Codex: —
- Gemini Pro Latest: 68.8
Agentic work
AutomationBench-AA
Workflow automation, penalized for guardrail violations
- GPT 5.2 Codex: —
- Gemini Pro Latest: 35.4%
AutomationBench-AA tasks completed
Workflows finished end to end without a guardrail violation
- GPT 5.2 Codex: —
- Gemini Pro Latest: 9.4%
Harvey LAB-AAv1.1
Legal tasks passed in full, with no material hallucination
- GPT 5.2 Codex: —
- Gemini Pro Latest: 0.0%
AA-Briefcasev1.1
Agentic knowledge work, rated head to head
- GPT 5.2 Codex: —
- Gemini Pro Latest: 456 Elo
GDPval-AAv2.1
Economically valuable occupational tasks, rated head to head
- GPT 5.2 Codex: —
- Gemini Pro Latest: 791 Elo
Document reasoning
GDP.pdf
Professional reasoning over PDF documents, all-pass rate
- GPT 5.2 Codex: —
- Gemini Pro Latest: 17.8%
AA-LCRv1.1
Reasoning across long documents
- GPT 5.2 Codex: 82.3%Top
- Gemini Pro Latest: 82.0%
MLCR-AA
Long-context reasoning over medical records
- GPT 5.2 Codex: —
- Gemini Pro Latest: 11.1%
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- GPT 5.2 Codex: 35.7%
- Gemini Pro Latest: 47.0%Top
GPQA Diamond
Graduate-level science questions
- GPT 5.2 Codex: 89.9%
- Gemini Pro Latest: 94.1%Top
IFBench
Following precise output instructions
- GPT 5.2 Codex: 77.6%Top
- Gemini Pro Latest: 77.1%
Coding
Terminal-Benchv4.0
Practical software engineering in a terminal
- GPT 5.2 Codex: —
- Gemini Pro Latest: 4.0%
SciCode
Scientific computing in Python
- GPT 5.2 Codex: —
- Gemini Pro Latest: 58.7%
Legacy evaluations
Terminal-Bench Hard
Earlier terminal task suite
- GPT 5.2 Codex: 37.1%
- Gemini Pro Latest: 53.8%Top
τ²-Bench Telecom
Tool use in a customer-support simulation
- GPT 5.2 Codex: 92.1%
- Gemini Pro Latest: 95.6%Top
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- GPT 5.2 Codex: 82.3%Top
- Gemini Pro Latest: 82.0%
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.
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
Related models
Other OpenAI models, starting with the same family.