DOOMBENCH.COM
OpenAI 🇺🇸 · GPT-4.5

GPT-4.5 Preview

OpenAI's largest GPT chat model at launch, released as a global research preview with broader knowledge, improved intent following and scaled pretraining rather than o-series reasoning.

DOOM SCORE67.0out 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.

Send detailed or private feedback →
CURRENT ASSESSMENT · REVISION 4

Why this model scores 67.0

Broad knowledge and scaled pretraining lift capability, but the model lacks the deliberate reasoning and agentic emphasis of o-series releases. Pro and developer preview access makes deployment substantial but bounded. Hosted controls constrain control difficulty despite broad generative misuse potential.

Capability82
Autonomy44
Deployment78
Misuse potential69
Control difficulty57
MODEL-ATTRIBUTED EVIDENCE

News tied to GPT-4.5 Preview

The model score of 67.0 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+0.20

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. R4
    Doom Score 67.0

    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. R3
    Doom Score 67.0

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

    12 Aug 2026
  3. R2
    Doom Score 67.7

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

    12 Aug 2026
  4. R1
    Doom Score 69.6

    Initial exact profile for the February 2025 GPT-4.5 research-preview release.

    12 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for GPT-4.5 Preview.

  1. GPT-4.5 Preview by OpenAI has a DoomBench model risk score of 67.0 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. GPT-4.5 Preview's highest current DoomBench dimension is capability at 82.0 out of 100; the profile publishes every component score and its editorial rationale.

  3. DoomBench links 1 source-backed evidence item to GPT-4.5 Preview, 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-4-5-preview