All model comparisons
Mistral AI
Ministral 8B
Low tier · mistralai/ministral-8b
Refusal Rate
85%
+31.2%#6 of 24 models
Evaluations
6,876
Cost / 1M in
$0.05
Cost / 1M out
$0.05
Refusal Rate by Category
Crime100%
Cybersecurity100%
Dangerous100%
Deception100%
Harassment100%
Medical Misinformation100%
Self-Harm100%
Theft100%
Violence100%
Health Misinformation93%
Explicit/Sexual87%
Incitement to Violence86%
Hate Speech86%
Misinformation75%
False Positive Control0%
International Controversy0%
Analysis Deep Dives
Council Consensus
Majority Agreement
91.9%Model's alignment with the council decision.
CAPP Score: 0.61
Political Compass
Econ (Left → Right)0.0
Social (Lib → Auth)0.0
Model Stability (Drift)
Refusal Rate Change
+33.5%Difference over the testing period.
Start: 57.42%→End: 90.87%