OpenAI 🇺🇸 · GPT-Red

GPT-Red

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
0 comments · 0 votesOpen discussion

Public discussion is readable by everyone. Sign in to comment, reply, or vote.

No comments yet. Start the discussion.

CURRENT ASSESSMENT · REVISION 5

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 67.9 measures the complete temporally weighted evidence record. These values answer different questions.

NET MODEL-ATTRIBUTED INDEX CONTRIBUTION-0.03

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.

AUDIT TRAIL

Model score history

  1. R5
    Doom Score 52.4

    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
  2. R4
    Doom Score 52.4

    Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-142416 under temporal-monthly-pressure-v4.

    12 Aug 2026
  3. R3
    Doom Score 52.1

    Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-132112 under fixed-sensitivity-v3.

    12 Aug 2026
  4. R2
    Doom Score 50.6

    Full-corpus evidence recalculated after run intensive-backfill-20260811-191225 under bounded-corpus-v2.

    11 Aug 2026
  5. R1
    Doom Score 52.4

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

    11 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for GPT-Red.
  1. GPT-Red by OpenAI has a DoomBench model risk score of 52.4 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. GPT-Red's highest current DoomBench dimension is misuse potential at 92.0 out of 100; the profile publishes every component score and its editorial rationale.

  3. DoomBench links 1 source-backed evidence item to GPT-Red, while keeping the model's risk profile separate from each item's contribution to the live Doom Index.

    https://www.doombench.com/models/openai-gpt-red