OpenAI 🇺🇸 · gpt-oss

gpt-oss-120b

Open-weight 120-billion-parameter reasoning model with tool use and visible chain-of-thought.

DOOM SCORE83.6out 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 3

Why this model scores 83.6

Near-frontier reasoning and tool use drive high capability and autonomy; unrestricted weights create maximal diffusion, strong misuse readiness and difficult containment.

Capability82
Autonomy77
Deployment100
Misuse potential79
Control difficulty84
MODEL-ATTRIBUTED EVIDENCE

News tied to gpt-oss-120b

The model score of 83.6 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+0.12

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.

Race TOWARD

OpenAI releases open-weight gpt-oss models

OpenAI released gpt-oss-120b and gpt-oss-20b under an open license, with reasoning, tool use and visible chain-of-thought for local and hosted deployment.

Full item contribution
+0.18
gpt-oss-120b equal share
+0.09
Read assessment →
AUDIT TRAIL

Model score history

  1. R3
    Doom Score 83.6

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

    12 Aug 2026
  2. R2
    Doom Score 83.5

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

    12 Aug 2026
  3. R1
    Doom Score 83.1

    New exact August 2025 open-weight model profile verified by OpenAI.

    12 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for gpt-oss-120b.
  1. gpt-oss-120b by OpenAI has a DoomBench model risk score of 83.6 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. gpt-oss-120b's highest current DoomBench dimension is deployment at 100.0 out of 100; the profile publishes every component score and its editorial rationale.

  3. DoomBench links 2 source-backed evidence items to gpt-oss-120b, 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-oss-120b