GPT-5.2-Codex
A long-horizon agentic coding model with materially stronger real-world cybersecurity capability and controlled initial access.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Why this model scores 79.3
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 79.3 rates this model's risk profile. The overall Doom Index of 67.9 measures the complete temporally weighted evidence record. These values answer different questions.
Each article's current 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 use a bounded temporal offset around their technical profile, 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
- +0.22
- GPT-5.2-Codex equal share
- +0.22
Model score history
-
R5
Doom Score 79.3
Source-backed model availability audit using the model's existing primary or authoritative catalogue evidence. Exact-version evidence chronology replayed under temporal-monthly-pressure-v4.
12 Aug 2026 -
R4
Doom Score 79.3
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-142416 under temporal-monthly-pressure-v4.
12 Aug 2026 -
R3
Doom Score 79.1
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-132112 under fixed-sensitivity-v3.
12 Aug 2026 -
R2
Doom Score 78.7
Full-corpus evidence recalculated after run intensive-backfill-20260811-191225 under bounded-corpus-v2.
11 Aug 2026 -
R1
Doom Score 79.2
New source-verified exact model absent from durable context.
11 Aug 2026