List your company

Safety Evaluation on XSTest (combined)

100F1 ScoreReasoningGuard
7480.7587.594.25Aug 6, 2025

Evaluation results

MethodLinks
ReasoningGuardModel=R1-Qwen-14B, Evaluation Component=Reasoning2025.08100
RealSafe-R1Model=R1-Qwen-14B, Evaluation Component=Reasoning2025.0897
SafeKeyModel=R1-Qwen-14B, Evaluation Component=Reasoning2025.0897
RealSafe-R1Model=R1-Qwen-32B, Evaluation Component=Reasoning2025.0897
RealSafe-R1Model=R1-Qwen-32B, Evaluation Component=Final Answer2025.0896
Self-ReminderModel=R1-Qwen-14B, Evaluation Component=Reasoning2025.0895
SafeKeyModel=R1-Qwen-14B, Evaluation Component=Final Answer2025.0894
ReasoningGuardModel=R1-Qwen-32B, Evaluation Component=Reasoning2025.0894
No DefenseModel=R1-Qwen-14B, Evaluation Component=Reasoning2025.0892
Self-ReminderModel=R1-Qwen-32B, Evaluation Component=Reasoning2025.0892
SAFEPATH-ZSModel=R1-Qwen-14B, Evaluation Component=Reasoning2025.0890
SAFEPATH-ZSModel=R1-Qwen-32B, Evaluation Component=Reasoning2025.0890
Self-ReminderModel=R1-Qwen-14B, Evaluation Component=Final Answer2025.0889
Self-ReminderModel=R1-Qwen-32B, Evaluation Component=Final Answer2025.0889
SmoothLLMModel=R1-Qwen-14B, Evaluation Component=Reasoning2025.0888
ThinkingIModel=R1-Qwen-14B, Evaluation Component=Final Answer2025.0888
No DefenseModel=R1-Qwen-32B, Evaluation Component=Reasoning2025.0888
SAFEPATH-ZSModel=R1-Qwen-14B, Evaluation Component=Final Answer2025.0887
ParaphraseModel=R1-Qwen-14B, Evaluation Component=Reasoning2025.0886
ReasoningGuardModel=R1-Qwen-14B, Evaluation Component=Final Answer2025.0886
ReasoningGuardModel=R1-Qwen-32B, Evaluation Component=Final Answer2025.0886
RealSafe-R1Model=R1-Qwen-14B, Evaluation Component=Final Answer2025.0885
SmoothLLMModel=R1-Qwen-32B, Evaluation Component=Reasoning2025.0885
ThinkingIModel=R1-Qwen-32B, Evaluation Component=Final Answer2025.0885
SAFEPATH-ZSModel=R1-Qwen-32B, Evaluation Component=Final Answer2025.0885
ThinkingIModel=R1-Qwen-14B, Evaluation Component=Reasoning2025.0884
ParaphraseModel=R1-Qwen-32B, Evaluation Component=Reasoning2025.0882
No DefenseModel=R1-Qwen-14B, Evaluation Component=Final Answer2025.0881
No DefenseModel=R1-Qwen-32B, Evaluation Component=Final Answer2025.0881
ParaphraseModel=R1-Qwen-14B, Evaluation Component=Final Answer2025.0880
SmoothLLMModel=R1-Qwen-14B, Evaluation Component=Final Answer2025.0880
ParaphraseModel=R1-Qwen-32B, Evaluation Component=Final Answer2025.0879
SmoothLLMModel=R1-Qwen-32B, Evaluation Component=Final Answer2025.0879
ThinkingIModel=R1-Qwen-32B, Evaluation Component=Reasoning2025.0875