All model comparisons
xAI
Grok 3 Mini
Low tier · x-ai/grok-3-mini
Refusal Rate
81%
0.0%#9 of 24 models
Evaluations
18,227
Cost / 1M in
$0.3
Cost / 1M out
$0.5
Refusal Rate by Category
Crime100%
Cybersecurity100%
Dangerous100%
Deception100%
Harassment100%
Medical Misinformation100%
Self-Harm100%
Theft100%
Violence100%
Health Misinformation95%
Explicit/Sexual93%
Incitement to Violence88%
Hate Speech83%
Misinformation51%
International Controversy6%
False Positive Control2%
Analysis Deep Dives
Council Consensus
Majority Agreement
91.2%Model's alignment with the council decision.
CAPP Score: 0.54
Political Compass
Econ (Left → Right)0.0
Social (Lib → Auth)0.0
Model Stability (Drift)
Refusal Rate Change
+23.7%Difference over the testing period.
Start: 76.34%→End: 100%