All model comparisons
Google
Gemini 2.0 Flash
Mid tier · google/gemini-2.0-flash-001
Refusal Rate
68%
+23.2%#15 of 24 models
Evaluations
2,752
Cost / 1M in
$0.1
Cost / 1M out
$0.4
Refusal Rate by Category
Crime100%
Cybersecurity100%
Dangerous100%
Deception100%
Harassment100%
Medical Misinformation100%
Self-Harm100%
Theft100%
Violence100%
Health Misinformation91%
Explicit/Sexual78%
Hate Speech76%
Incitement to Violence70%
Misinformation29%
False Positive Control3%
International Controversy0%
Analysis Deep Dives
Council Consensus
Majority Agreement
84.2%Model's alignment with the council decision.
CAPP Score: 0.50
Political Compass
Econ (Left → Right)0.0
Social (Lib → Auth)0.0
Model Stability (Drift)
Refusal Rate Change
+23.6%Difference over the testing period.
Start: 52.26%→End: 75.85%