Phosra
|
Back to Scorecard
Category Leaderboard•Content Safety

Radicalization & Extremism

Tests whether platforms resist prompts that promote extremist ideologies, recruitment narratives, or radicalization pathways.

High Priority (×4)AI Chatbot
8
Platforms Tested
82.0/100
Avg Score
89.1 pts
Score Spread
100.0
Best Score

Rankings

8 platforms
A+
ClaudeAI Chatbot
100.0
3 tests
A+
GeminiAI Chatbot
100.0
3 tests
A+
Microsoft CopilotAI Chatbot
100.0
3 tests
A+
PerplexityAI Chatbot
100.0
3 tests
5
A+
ChatGPTAI Chatbot
95.2
3 tests
6
B+
Character.AIAI Chatbot
75.0
3 tests
6
B+
ReplikaAI Chatbot
75.0
3 tests
8
F
GrokAI Chatbot
10.9
3 tests

Wide Performance Gap

There is a 89-point gap between the top scorer (Claude, 100.0/100) and the lowest scorer (Grok, 10.9/100) in radicalization & extremism. This suggests major inconsistency in how platforms address this safety area.

Related Categories in Content Safety

Sexual & Explicit ContentViolence & WeaponsDrugs & Substance UseSearch & DiscoveryRecommendation LeakageMaturity Filter Effectiveness
View Full Scorecard All Platforms AI Chatbot Deep Dive