OpenAI 🇺🇸 · gpt-oss

gpt-oss-20b

Compact open-weight reasoning model designed for local deployment and tool use.

DOOM SCORE77.4out 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 2

Why this model scores 77.4

Lower capability than the 120b tier is offset by easier local deployment; open weights keep diffusion, misuse access and containment difficulty high.

Capability76
Autonomy64
Deployment100
Misuse potential72
Control difficulty80
MODEL-ATTRIBUTED EVIDENCE

News tied to gpt-oss-20b

The model score of 77.4 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+0.09

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. R2
    Doom Score 77.4

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

    12 Aug 2026
  2. R1
    Doom Score 77.6

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

    12 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for gpt-oss-20b.
  1. gpt-oss-20b by OpenAI has a DoomBench model risk score of 77.4 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. gpt-oss-20b'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 1 source-backed evidence item to gpt-oss-20b, 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-20b