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.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
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.
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.
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.
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
Model score history
-
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 -
R2
Doom Score 69.0
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-132112 under fixed-sensitivity-v3.
12 Aug 2026 -
R1
Doom Score 71.6
Initial exact source-backed profile for the original DeepSeek-V3 release.
12 Aug 2026