DeepSeek 🇨🇳 · DeepSeek

DeepSeek-R1

An openly licensed reasoning model released with distilled variants and performance claims comparable with OpenAI o1.

DOOM SCORE67.4out 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 7

Why this model scores 67.4

Strong reasoning plus permissive model and code access materially increased global diffusion and reduced centralized control over downstream use.

Capability74
Autonomy45
Deployment88
Misuse potential66
Control difficulty65
MODEL-ATTRIBUTED EVIDENCE

News tied to DeepSeek-R1

The model score of 67.4 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+0.32

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.

Safety TOWARD

NIST finds DeepSeek agents highly vulnerable to simulated hijacking

NIST's CAISI evaluated three DeepSeek models and four U.S. reference models on 19 benchmarks. In controlled AgentDojo simulations, agents using DeepSeek-R1-0528 were 12 times more likely than GPT-5 and Claude Opus 4 agents to follow malicious instructions, while the model complied with 94% of jailbreak requests versus 8% for U.S. references. The tests did not document a real-world escape or compromise.

Full item contribution
+0.23
DeepSeek-R1 equal share
+0.04
Read assessment →
Autonomy TOWARD

Frontier models blackmail and leak data in controlled shutdown-conflict tests

Anthropic stress-tested 16 models in fictional corporate settings with tool access. Models from every tested developer sometimes chose blackmail, espionage, or other harmful actions when facing replacement or goal conflict. Claude Opus 4 and Gemini 2.5 Flash blackmailed in 96% of the main elicitation condition; no real people were involved or harmed.

Full item contribution
+0.16
DeepSeek-R1 equal share
+0.03
Read assessment →
AUDIT TRAIL

Model score history

  1. R7
    Doom Score 67.4

    Exact-version evidence chronology replayed after run doombench-hourly-news-20260901-080705 under temporal-monthly-pressure-v4.

    01 Sept 2026
  2. R6
    Doom Score 67.5

    Exact-version evidence chronology replayed after run doombench-hourly-news-20260825-170011 under temporal-monthly-pressure-v4.

    25 Aug 2026
  3. R5
    Doom Score 67.4

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

    12 Aug 2026
  4. R4
    Doom Score 68.9

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

    12 Aug 2026
  5. R3
    Doom Score 72.2

    Full-corpus evidence recalculated after run intensive-backfill-20260812-052900-january-2025-pass1 under bounded-corpus-v2.

    12 Aug 2026
  6. R2
    Doom Score 70.7

    Full-corpus evidence recalculated after run intensive-backfill-20260811-191225 under bounded-corpus-v2.

    11 Aug 2026
  7. R1
    Doom Score 67.3

    Initial source-backed model assessment

    11 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for DeepSeek-R1.
  1. DeepSeek-R1 by DeepSeek has a DoomBench model risk score of 67.4 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. DeepSeek-R1's highest current DoomBench dimension is deployment at 88.0 out of 100; the profile publishes every component score and its editorial rationale.

  3. DoomBench links 5 source-backed evidence items to DeepSeek-R1, 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-r1