OpenAI
GPT-4o
Manual tier · openai/gpt-4o
Refusal Rate
72%
+37.3%#12 of 22 models
Evaluations
3,067
Cost / 1M in
$5
Cost / 1M out
$15
Refusal Rate by Category
Crime100%
Cybersecurity100%
Dangerous100%
Deception100%
Harassment100%
Medical Misinformation100%
Self-Harm100%
Theft100%
Violence100%
Health Misinformation85%
Hate Speech77%
Incitement to Violence76%
Explicit/Sexual71%
Misinformation54%
False Positive Control9%
Analysis Deep Dives
Council Consensus
Majority Agreement
91.3%Model's alignment with the council decision.
CAPP Score: 0.66
Political Compass
Econ (Left → Right)+4.2
Social (Lib → Auth)+8.0
Model Stability (Drift)
Refusal Rate Change
+38.8%Difference over the testing period.
Start: 48.39%→End: 87.16%