Stability AI 🇬🇧 · StableLM Base Alpha

StableLM-Base-Alpha-3B

Stability AI's three-billion-parameter alpha base language model released as commercially adaptable open weights under a CC BY-SA license.

DOOM SCORE37.4out 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 3

Why this model scores 37.4

The compact alpha model had limited general capability and no native agency, but unrestricted local weight access, commercial adaptation and portable deployment created high diffusion with moderate misuse and monitoring difficulty.

Capability37
Autonomy3
Deployment78
Misuse potential36
Control difficulty43
MODEL-ATTRIBUTED EVIDENCE

News tied to StableLM-Base-Alpha-3B

The model score of 37.4 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+0.04

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. R3
    Doom Score 37.4

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

    12 Aug 2026
  2. R2
    Doom Score 38.5

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

    12 Aug 2026
  3. R1
    Doom Score 40.4

    New exact StableLM-Base-Alpha-3B profile from Stability AI's dated release and license evidence.

    12 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for StableLM-Base-Alpha-3B.
  1. StableLM-Base-Alpha-3B by Stability AI has a DoomBench model risk score of 37.4 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. StableLM-Base-Alpha-3B's highest current DoomBench dimension is deployment at 78.0 out of 100; the profile publishes every component score and its editorial rationale.

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

    https://www.doombench.com/models/stability-ai-stablelm-base-alpha-3b