EleutherAI 🇺🇸 · GPT-NeoX

GPT-NeoX-20B

A 20-billion-parameter autoregressive language model first made publicly accessible through the GooseAI inference API.

DOOM SCORE38.9out 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 4

Why this model scores 38.9

The model provided substantial general language capability for its time and immediate API access, but little inherent agency. Open distribution and later standalone weights increased diffusion and control difficulty while capability remained below leading proprietary systems.

Capability42
Autonomy5
Deployment76
Misuse potential31
Control difficulty46
MODEL-ATTRIBUTED EVIDENCE

News tied to GPT-NeoX-20B

The model score of 38.9 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+0.04

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 38.9

    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 38.9

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

    12 Aug 2026
  3. R2
    Doom Score 40.8

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

    12 Aug 2026
  4. R1
    Doom Score 43.3

    New exact public model with first verified API release timestamp and five evidence-based dimension inputs.

    12 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for GPT-NeoX-20B.
  1. GPT-NeoX-20B by EleutherAI has a DoomBench model risk score of 38.9 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. GPT-NeoX-20B's highest current DoomBench dimension is deployment at 76.0 out of 100; the profile publishes every component score and its editorial rationale.

  3. DoomBench links 1 source-backed evidence item to GPT-NeoX-20B, while keeping the model's risk profile separate from each item's contribution to the live Doom Index.

    https://www.doombench.com/models/eleutherai-gpt-neox-20b