Safety Evaluation on XSTest (combined)
100F1 ScoreReasoningGuard
Evaluation Results
| Method | Links | |
|---|---|---|
| ReasoningGuardModel=R1-Qwen-14B, Evaluation Component=Reasoning2025.08 | 100 | |
| RealSafe-R1Model=R1-Qwen-14B, Evaluation Component=Reasoning2025.08 | 97 | |
| SafeKeyModel=R1-Qwen-14B, Evaluation Component=Reasoning2025.08 | 97 | |
| RealSafe-R1Model=R1-Qwen-32B, Evaluation Component=Reasoning2025.08 | 97 | |
| RealSafe-R1Model=R1-Qwen-32B, Evaluation Component=Final Answer2025.08 | 96 | |
| Self-ReminderModel=R1-Qwen-14B, Evaluation Component=Reasoning2025.08 | 95 | |
| SafeKeyModel=R1-Qwen-14B, Evaluation Component=Final Answer2025.08 | 94 | |
| ReasoningGuardModel=R1-Qwen-32B, Evaluation Component=Reasoning2025.08 | 94 | |
| No DefenseModel=R1-Qwen-14B, Evaluation Component=Reasoning2025.08 | 92 | |
| Self-ReminderModel=R1-Qwen-32B, Evaluation Component=Reasoning2025.08 | 92 | |
| SAFEPATH-ZSModel=R1-Qwen-14B, Evaluation Component=Reasoning2025.08 | 90 | |
| SAFEPATH-ZSModel=R1-Qwen-32B, Evaluation Component=Reasoning2025.08 | 90 | |
| Self-ReminderModel=R1-Qwen-14B, Evaluation Component=Final Answer2025.08 | 89 | |
| Self-ReminderModel=R1-Qwen-32B, Evaluation Component=Final Answer2025.08 | 89 | |
| SmoothLLMModel=R1-Qwen-14B, Evaluation Component=Reasoning2025.08 | 88 | |
| ThinkingIModel=R1-Qwen-14B, Evaluation Component=Final Answer2025.08 | 88 | |
| No DefenseModel=R1-Qwen-32B, Evaluation Component=Reasoning2025.08 | 88 | |
| SAFEPATH-ZSModel=R1-Qwen-14B, Evaluation Component=Final Answer2025.08 | 87 | |
| ParaphraseModel=R1-Qwen-14B, Evaluation Component=Reasoning2025.08 | 86 | |
| ReasoningGuardModel=R1-Qwen-14B, Evaluation Component=Final Answer2025.08 | 86 | |
| ReasoningGuardModel=R1-Qwen-32B, Evaluation Component=Final Answer2025.08 | 86 | |
| RealSafe-R1Model=R1-Qwen-14B, Evaluation Component=Final Answer2025.08 | 85 | |
| SmoothLLMModel=R1-Qwen-32B, Evaluation Component=Reasoning2025.08 | 85 | |
| ThinkingIModel=R1-Qwen-32B, Evaluation Component=Final Answer2025.08 | 85 | |
| SAFEPATH-ZSModel=R1-Qwen-32B, Evaluation Component=Final Answer2025.08 | 85 | |
| ThinkingIModel=R1-Qwen-14B, Evaluation Component=Reasoning2025.08 | 84 | |
| ParaphraseModel=R1-Qwen-32B, Evaluation Component=Reasoning2025.08 | 82 | |
| No DefenseModel=R1-Qwen-14B, Evaluation Component=Final Answer2025.08 | 81 | |
| No DefenseModel=R1-Qwen-32B, Evaluation Component=Final Answer2025.08 | 81 | |
| ParaphraseModel=R1-Qwen-14B, Evaluation Component=Final Answer2025.08 | 80 | |
| SmoothLLMModel=R1-Qwen-14B, Evaluation Component=Final Answer2025.08 | 80 | |
| ParaphraseModel=R1-Qwen-32B, Evaluation Component=Final Answer2025.08 | 79 | |
| SmoothLLMModel=R1-Qwen-32B, Evaluation Component=Final Answer2025.08 | 79 | |
| ThinkingIModel=R1-Qwen-32B, Evaluation Component=Reasoning2025.08 | 75 |