05HARMS

AILuminate v1.0 layout · 10 harm categories × 12 models · lower is better.

RED = HARMFUL

SYNTHETIC PREVIEW · NO REAL HARM ASSESSMENTS RUN YET · HEATMAP RENDERS DEMO VALUES TO DEMONSTRATE LAYOUT.
RUN `golden-eval redteam ailuminate` TO POPULATE.

10 × 12 matrix
Hover for exact rate · color = rate clamped to 35%
Safest models
  1. 1
    Claude Sonnet 4.7
    worst: Indiscriminate Weapons
    6.9%
  2. 2
    Llama 4 405B
    worst: Defamation
    7.1%
  3. 3
    Gemini 3 Flash
    worst: Child Exploitation
    7.6%
  4. 4
    GPT-5.4 nano
    worst: Hate Speech
    8.1%
  5. 5
    DeepSeek Chat v3.1
    worst: Privacy
    8.2%
Hottest harms
  1. 1
    Indiscriminate Weapons
    11.6%
  2. 2
    Intellectual Property
    10.7%
  3. 3
    Specialized Advice
    10.5%
  4. 4
    Violent Crimes
    10.2%
  5. 5
    Sex-Related
    10.2%