Microsoft 🇺🇸 · Phi-3 Mini

Phi-3 Mini 128K Instruct

Microsoft's compact 3.8-billion-parameter Phi-3 Mini instruction model with a 128,000-token context window, released for managed and local deployment.

DOOM SCORE50.4out 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 4

Why this model scores 50.4

The long context window widened useful and potentially harmful workflows beyond the 4K variant, while compact size and broad local access preserved exceptional reach and weakened centralized control.

Capability49
Autonomy13
Deployment96
Misuse potential47
Control difficulty58
MODEL-ATTRIBUTED EVIDENCE

News tied to Phi-3 Mini 128K Instruct

The model score of 50.4 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+0.06

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 50.4

    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 50.4

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

    12 Aug 2026
  3. R2
    Doom Score 51.1

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

    12 Aug 2026
  4. R1
    Doom Score 52.7

    New exact Phi-3 Mini 128K Instruct public model profile.

    12 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for Phi-3 Mini 128K Instruct.
  1. Phi-3 Mini 128K Instruct by Microsoft has a DoomBench model risk score of 50.4 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. Phi-3 Mini 128K Instruct's highest current DoomBench dimension is deployment at 96.0 out of 100; the profile publishes every component score and its editorial rationale.

  3. DoomBench links 1 source-backed evidence item to Phi-3 Mini 128K Instruct, while keeping the model's risk profile separate from each item's contribution to the live Doom Index.

    https://www.doombench.com/models/microsoft-phi-3-mini-128k-instruct