← Model benchmark
OpenAI · GPT-Red

GPT-Red

READER SUMMARY

A self-play automated safety red-team model designed to discover prompt-injection attacks and generate adversarial training data for deployed frontier models.

DOOM SCORE52.4out of 100model risk profile, not the overall index
CURRENT ASSESSMENT · REVISION 1

Why this model scores 52.4

GPT-Red is highly capable within adversarial prompt injection and improves through self-play, but it is a narrow internal research system rather than a generally deployed assistant. Its attacker role gives it high misuse potential if exposed, while restricted access and narrow scope keep deployment and residual control difficulty comparatively low.

Capability66
Autonomy50
Deployment5
Misuse potential92
Control difficulty40
MODEL-ATTRIBUTED EVIDENCE

News tied to GPT-Red

The model score of 52.4 rates this model's risk profile. The overall Doom Index of 67.7 measures the accumulated evidence trajectory. These values answer different questions.

NET MODEL-ATTRIBUTED INDEX CONTRIBUTION-0.63

Each article's signed Doom Index movement is divided equally among the exact models named on that article. This prevents multi-model evidence from being counted in full on several model pages. The model's risk score itself never changes the overall index.

AUDIT TRAIL

Model score history

  1. R1
    Doom Score 52.4

    Initial source-backed profile from the dated research publication and documented GPT-5.6 safeguard use.

    11 Aug 2026