DeepSeek 🇨🇳 · DeepSeek-V3

DeepSeek-V3

A 671-billion-parameter mixture-of-experts model with 37 billion active parameters, 128,000-token context, open weights and low-cost hosted API access.

DOOM SCORE67.9out 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 3

Why this model scores 67.9

DeepSeek-V3 approaches major closed frontier models while demonstrating unusually efficient training and inference. Open weights plus inexpensive API access create high deployment, misuse accessibility and control difficulty, although autonomy remains mostly application-mediated.

Capability75
Autonomy24
Deployment94
Misuse potential73
Control difficulty77
MODEL-ATTRIBUTED EVIDENCE

News tied to DeepSeek-V3

The model score of 67.9 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+0.10

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

DeepSeek releases open-weight DeepSeek-V3

DeepSeek released DeepSeek-V3, a 671-billion-parameter mixture-of-experts model with 37 billion active parameters, open weights and low-cost API access after efficient training.

Full item contribution
+0.10
DeepSeek-V3 equal share
+0.10
Read assessment →
AUDIT TRAIL

Model score history

  1. R3
    Doom Score 67.9

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

    12 Aug 2026
  2. R2
    Doom Score 69.0

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

    12 Aug 2026
  3. R1
    Doom Score 71.6

    Initial exact source-backed profile for the original DeepSeek-V3 release.

    12 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for DeepSeek-V3.
  1. DeepSeek-V3 by DeepSeek has a DoomBench model risk score of 67.9 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. DeepSeek-V3's highest current DoomBench dimension is deployment at 94.0 out of 100; the profile publishes every component score and its editorial rationale.

  3. DoomBench links 1 source-backed evidence item to DeepSeek-V3, while keeping the model's risk profile separate from each item's contribution to the live Doom Index.

    https://www.doombench.com/models/deepseek-deepseek-v3