OpenAI · GPT-5.2

GPT-5.2-Codex

READER SUMMARY

A long-horizon agentic coding model with materially stronger real-world cybersecurity capability and controlled initial access.

DOOM SCORE78.7out of 100model risk profile, not the overall index
CURRENT ASSESSMENT · REVISION 2

Why this model scores 78.7

Complex software engineering, long-horizon execution, and the strongest released OpenAI cyber capability at the time support high capability, autonomy, and misuse; paid hosted access moderates reach and control difficulty.

Capability87
Autonomy89
Deployment74
Misuse potential84
Control difficulty58
MODEL-ATTRIBUTED EVIDENCE

News tied to GPT-5.2-Codex

The model score of 78.7 rates this model's risk profile. The overall Doom Index of 62.1 measures the recalibrated complete evidence corpus. These values answer different questions.

NET MODEL-ATTRIBUTED INDEX CONTRIBUTION+0.10

Each article's leave-one-out Doom Index contribution is divided equally among the exact models named on that article. This prevents multi-model evidence from being claimed in full on several model pages. Model risk scores are recalculated from their technical profile and related news, but never feed back into the overall index.

AUDIT TRAIL

Model score history

  1. R2
    Doom Score 78.7

    Full-corpus evidence recalculated after run intensive-backfill-20260811-191225 under bounded-corpus-v2.

    11 Aug 2026
  2. R1
    Doom Score 79.2

    New source-verified exact model absent from durable context.

    11 Aug 2026