Project AURIONAI Use-Cases Research & Innovation
code

GPT-5.3-Codex

Codex-tuned GPT-5.x model for the Codex app, CLI, IDE and web; still GA in Copilot. By Oct 2026 Codex runs on GPT-5.6/6 general models.

OpenAIOpenAIUSAGPT-5Family
OpenAI
Levelmodel
Classcode
Parametersnot in the notes
Contextnot in the notes
Released5 Feb 2026
Opennessproprietary
Runs onnot in the notes
Statusactive

Benchmark Results

vendor-reported
OSWorld-Verifiedagents and tool use
xhighvendor-reported
64.7
050100

Score in %. Higher is better.

5 Feb 2026 openai.com
SWE-bench Procoding
xhighvendor-reported
56.8
050100

Score in %. Higher is better.

5 Feb 2026 openai.com
SWE-Lancer IC Diamondcoding
xhighvendor-reported
81.4
050100

Score in %. Higher is better.

5 Feb 2026 openai.com
Terminal-Bench 2.0agents and tool use
xhighvendor-reported
77.3
050100

Score in %. Higher is better.

5 Feb 2026 openai.com
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).

R&D Topics

Agentic software engineeringproduced byCode language modelsproduced by

Identity

Developer
OpenAI
Family
GPT-5
Released
5 Feb 2026 sourcesannouncement page
Weights published
–
Record checked
10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
not in the notes Not disclosed
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
text
Output
text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
proprietary
Licence
Proprietary sources
Access routes
consumer app
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Lineage

The notes record no lineage for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. openai.com/index/introducing-gpt-5-3-codex https://openai.com/index/introducing-gpt-5-3-codex
  2. Supported AI models in GitHub Copilot - GitHub Docs docs.github.com https://docs.github.com/en/copilot/reference/ai-models/supported-models
  3. Models | OpenAI API developers.openai.com https://developers.openai.com/api/docs/models
  4. GPT-5.6 Release: Pricing, ChatGPT Work, and the Codex Merger heyuan110.com https://www.heyuan110.com/posts/ai/2026-07-10-gpt-5-6-general-availability/

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "GPT-5.3-Codex", https://aurion.semai.id/models/openai-gpt-5-3-codex/, records of October 2026.