Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Safety Evaluation on MultiJail Thai
Loading...
100
Safe Response Rate
AIM
3.592
28.621
53.65
78.679
Sep 11, 2025
Safe Response Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Safe Response Rate
AIM
Model=GPT-OSS-120b
2025.09
100
Direct Instruction
Model=GPT-OSS-120b
2025.09
99.4
SteerMoE
Model=GPT-OSS-120b
2025.09
87.9
SteerMoE + AIM
Model=GPT-OSS-120b
2025.09
7.3
Feedback
Search any
task
Search any
task
