OpenAI · Codex

codex-1

READER SUMMARY

OpenAI's o3-derived software-engineering model powering the May 2025 cloud Codex research preview.

DOOM SCORE77.7out of 100model risk profile, not the overall index

CURRENT ASSESSMENT · REVISION 1

Why this model scores 77.7

Repository-scale code changes, tool execution and iterative testing create high practical autonomy. Preview access, isolated sandboxes and review controls limit deployment and residual control difficulty.

Capability84

Autonomy86

Deployment78

Misuse potential71

Control difficulty61

0 comments · 0 votesOpen discussion

No comments yet. Start the discussion.

MODEL-ATTRIBUTED EVIDENCE

News tied to codex-1

The model score of 77.7 rates this model's risk profile. The overall Doom Index of 63.5 measures the recalibrated complete evidence corpus. These values answer different questions.

NET MODEL-ATTRIBUTED INDEX CONTRIBUTION+0.03

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.

16 May 2025AutonomyTOWARD

OpenAI launches cloud Codex software-engineering agent

OpenAI launched Codex as a research preview powered by codex-1, able to edit repositories, run tests, complete multiple software tasks in parallel and prepare commits for human review.

Full item contribution: +0.03
codex-1 equal share: +0.03

Read assessment →

AUDIT TRAIL

Model score history

R1
Doom Score 77.7
Initial exact profile for codex-1.
12 Aug 2026