GPT-5.3-Codex
A broadly capable long-running computer-work agent with High cyber classification and layered access safeguards.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Why this model scores 85.6
Strong coding, research, tool use, computer use, and professional-work breadth support high capability and autonomy; initial paid distribution and layered cyber safeguards temper deployment and control difficulty.
News tied to GPT-5.3-Codex
The model score of 85.6 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-5.3-Codex with high cyber classification
OpenAI released GPT-5.3-Codex for long-running computer work after using early versions in its own training and deployment process, while treating it as High cyber capability.
- Full item contribution
- +0.24
- GPT-5.3-Codex equal share
- +0.24
Model score history
-
R5
Doom Score 85.6
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 85.6
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-142416 under temporal-monthly-pressure-v4.
12 Aug 2026 -
R3
Doom Score 85.3
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-132112 under fixed-sensitivity-v3.
12 Aug 2026 -
R2
Doom Score 84.4
Full-corpus evidence recalculated after run intensive-backfill-20260811-191225 under bounded-corpus-v2.
11 Aug 2026 -
R1
Doom Score 85.6
New source-verified exact model absent from durable context.
11 Aug 2026