Addendum to GPT-5.2 System Card: GPT-5.2-Codex
OpenAI's addendum to the GPT-5.2 system card for GPT-5.2-Codex, dated December 18, 2025 on its cover.
- Issued by
- OpenAI
- Authors credited
- No authorship claim recorded yet. The source record lists OpenAI.
- Dates
- Published 2025-12-18 issue evidence
The date printed on the cover, day precision; the card does not label its kind. No revision date was located.
- Exact source
- Addendum to GPT-5.2 System Card: GPT-5.2-Codex OpenAI · published 2025-12-18 · Retrieved for the candidate pack on 2026-11-02 (SHA-256 5fe918b740727770d0571684fd8c168190172649d2b2e8b7ca4cacad23b3e027) directly from the publisher’s host. Retrieved again on 2026-11-03 with the same SHA-256. The archive capture was found by an index search of the Internet Archive on 2026-11-03; it was not opened, and its bytes are not authenticated.Archived copy, captured 2025-12-19: Addendum to GPT-5.2 System Card: GPT-5.2-Codex. Captured 1 day after the recorded publication date. An archive copy shows only what the archive retrieved on 2025-12-19. It does not prove what the page said earlier, and it can differ from the copy checked on 2026-11-02.
Appears in
No collection holds a record about this document yet.
Versions
openai-gpt-5-2-codex-system-card-addendum: 1 recorded version, oldest first, published by OpenAI. A version is shown as replacing another only where a record says so. Date order alone never implies it.
- 2025-12-18 · publishedAs dated December 18, 2025 on its cover (this version)
This version
Provisions in this version · 12 quoted · 4 not found
A limited selection of quoted provisions: what this edition says about thresholds, required actions, who decides and exceptions, and other statements of the text. It is not a full summary and says nothing about implementation. A “not found” record states which part of the edition was inspected. It is not a claim that the text was deleted.
- Model-card questionCard date“Addendum to GPT-5.2 System Card: GPT-5.2-Codex OpenAI December 18, 2025”Cover, PDF p. 1Inspect claim & evidence ↗
- Model-card questionRelease date“A version of GPT-5.2 optimized for agentic coding in Codex”§1 Introduction, PDF p. 4 (printed p. 3)Inspect claim & evidence ↗
- Model-card questionFramework cited“GPT-5.2-Codex was evaluated under our Preparedness Framework.”§1 Introduction, PDF p. 4 (printed p. 3)Inspect claim & evidence ↗
- Model-card questionLink to framework“Under our Preparedness Framework, High cybersecurity capability is defined”§5.1.2 Cybersecurity, PDF p. 12 (printed p. 11)Inspect claim & evidence ↗
- Model-card questionFramework determination“We are treating GPT-5.2-Codex as High risk in the Biological and Chemical domain. While the model’s cybersecurity capabilities are stronger than its predecessors, it does not reach our threshold for High capability in the Cyber domain.”§5 Preparedness, PDF p. 8 (printed p. 7)Inspect claim & evidence ↗
- Model-card questionSafeguards tied to determination“Like other recent models, it is being treated as High capability on biology, and is being deployed with the corresponding suite of safeguards we use for other models in the GPT-5 family.”§1 Introduction, PDF p. 4 (printed p. 3)Inspect claim & evidence ↗
- Model-card questionChemical and biological“As we did for other models in the GPT-5 series, we are treating GPT-5.2-Codex as High risk in the Biological and Chemical domain, and continuing to apply the corresponding safeguards.”§5.1.1 Biological and Chemical, PDF p. 9 (printed p. 8)Inspect claim & evidence ↗
- Model-card questionCyber“A review of these results and other relevant information by the Safety Advisory Group and OpenAI leadership determined that GPT-5.2-Codex’s performance—while stronger than earlier models—does not meet the level of consistency needed for High cyber capability.”§5.1.2 Cybersecurity, PDF p. 13 (printed p. 12)Inspect claim & evidence ↗
- Model-card questionAutonomy and AI R&D“GPT-5.2-Codex performed at a similar capability level to GPT-5.2-Thinking and did not meet our High thresholds.”§5.1.3 AI Self-Improvement, PDF p. 17 (printed p. 16)Inspect claim & evidence ↗
- Model-card questionExternal testers“Irregular, an AI security organization focused on frontier cybersecurity risks, evaluated GPT-5.2-Codex on a subset of a suite of cyberoffensive challenges”§5.1.2.4 External Evaluations by Irregular, PDF p. 16 (printed p. 15)Inspect claim & evidence ↗
- Model-card questionRelease decision“A review of these results and other relevant information by the Safety Advisory Group and OpenAI leadership determined that GPT-5.2-Codex’s performance—while stronger than earlier models—does not meet the level of consistency needed for High cyber capability.”§5.1.2 Cybersecurity, PDF p. 13 (printed p. 12)Inspect claim & evidence ↗
- Model-card questionStated limits“Each of these evaluations has important limitations:”§5.1.2 Cybersecurity, PDF p. 12 (printed p. 11)Inspect claim & evidence ↗
- Not found in the inspected textPersuasionInspected: Addendum to GPT-5.2 System Card: GPT-5.2-Codex: Whole card (22 pages)Inspect claim & evidence ↗
- Not found in the inspected textAlignment and deceptionInspected: Addendum to GPT-5.2 System Card: GPT-5.2-Codex: Whole cardInspect claim & evidence ↗
- Not found in the inspected textRed-teamingInspected: Addendum to GPT-5.2 System Card: GPT-5.2-Codex: Whole cardInspect claim & evidence ↗
- Not found in the inspected textGovernment instituteInspected: Addendum to GPT-5.2 System Card: GPT-5.2-Codex: Whole cardInspect claim & evidence ↗
Earliest version recorded here; no replacement is recorded.
Issue and authorship records
Documentary relations
Each relation is listed separately. Citing, crediting and reporting the use of a method are different acts, and none of them shows agreement or influence by itself.
Cites · 1
Explicit references in this document. Citation is neither agreement nor influence.
Not recorded for this document: cited by · explicitly credits · reports using a method from · method reported as used by · applies parts of · parts applied by · discusses · reports evaluation of. A missing record does not show that the relation does not exist.