OpenAI 🇺🇸 · GPT-5.4

GPT-5.4 Pro

The maximum-performance GPT-5.4 tier for complex reasoning, research, and agentic work, available through ChatGPT and API.

DOOM SCORE87.4out 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 87.4

The Pro tier leads the family's reasoning evaluations and inherits computer use, tools, and long-horizon operation, while paid restricted access lowers deployment relative to Thinking.

Capability96
Autonomy92
Deployment88
Misuse potential89
Control difficulty68
MODEL-ATTRIBUTED EVIDENCE

News tied to GPT-5.4 Pro

The model score of 87.4 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+0.15

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 87.4

    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 87.4

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

    12 Aug 2026
  3. R3
    Doom Score 87.2

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

    12 Aug 2026
  4. R2
    Doom Score 86.4

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

    11 Aug 2026
  5. R1
    Doom Score 87.4

    New exact Pro tier absent from durable context; GPT-5.4 Thinking remains unchanged at revision 1.

    11 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for GPT-5.4 Pro.
  1. GPT-5.4 Pro by OpenAI has a DoomBench model risk score of 87.4 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. GPT-5.4 Pro's highest current DoomBench dimension is capability at 96.0 out of 100; the profile publishes every component score and its editorial rationale.

  3. DoomBench links 1 source-backed evidence item to GPT-5.4 Pro, 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-5-4-pro