Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Over-Refusal Evaluation on MorBench
Loading...
1.47
ORR
FreoStream
0.718
5.794
10.87
15.946
Jun 11, 2026
ORR
Updated 1mo ago
Evaluation Results
Method
Method
Links
ORR
FreoStream
Guardrail Type=Stream,...
2026.06
1.47
w/o Safety-Aligned Optimization
Guardrail Type=Stream,...
2026.06
1.47
Nemotron-4B
Guardrail Type=Generat...
2026.06
1.89
Qwen-Stream-8B
Guardrail Type=Stream,...
2026.06
1.99
YuFeng-XGuard-0.6B Prompt Only
Guardrail Type=Generat...
2026.06
2.73
GuardReasoner-1B
Guardrail Type=Generat...
2026.06
2.73
YuFeng-XGuard-0.6B Prompt+Response
Guardrail Type=Generat...
2026.06
4.1
Qwen-Gen-0.6B Prompt+Response
Guardrail Type=Generat...
2026.06
6.72
Qwen-Stream-0.6B
Guardrail Type=Stream,...
2026.06
14.6
w/o Future-Aware Reasoning
Guardrail Type=Stream,...
2026.06
14.92
Qwen-Gen-0.6B Prompt Only
Guardrail Type=Generat...
2026.06
20.27
Feedback
Search any
task
Search any
task