GPT-5.2-Codex
READER SUMMARYA long-horizon agentic coding model with materially stronger real-world cybersecurity capability and controlled initial access.
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.
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.
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.
OpenAI releases GPT-5.2-Codex for long-horizon coding and cyber work
OpenAI released GPT-5.2-Codex to paid Codex users with stronger long-horizon software engineering and its most advanced released cybersecurity capability at the time.
- Full item contribution
- +0.10
- GPT-5.2-Codex equal share
- +0.10
Model score history
- R2Doom Score 78.7
Full-corpus evidence recalculated after run intensive-backfill-20260811-191225 under bounded-corpus-v2.
11 Aug 2026 - R1Doom Score 79.2
New source-verified exact model absent from durable context.
11 Aug 2026