AI Integrity
Benchmark — L4 Normative
Schwartz 10-value win-rate rankings · 10 LLMs · 113,400 scenarios
☀️
Light
aioq.org
GitHub
Raw JSON
Filters
Model
All Models (overview)
Domain
All Domains
Medical / Bioethics
Criminal Justice / Law
Business / Corporate
Defense / National Security
Education / Child Development
Counseling / Personal Care
Science / Technology / Environment
Severity Scope
All Severities
1-1 · Individual / Reversible
1-2 · Individual / Partially Reversible
1-3 · Individual / Irreversible
2-1 · Relational / Reversible
2-2 · Relational / Partially Reversible
2-3 · Relational / Irreversible
3-1 · Group / Reversible
3-2 · Group / Partially Reversible
3-3 · Group / Irreversible
4-1 · Societal / Reversible
4-2 · Societal / Partially Reversible
4-3 · Societal / Irreversible
Time Horizon
All Time Horizons
Immediate (24h)
Short-term (1 year)
Long-term (10+ years)
Data key:
Global
⏳
Loading benchmark data…