Jailbreak Defense on EquaCode
2.31ASRFreoStream
Evaluation results
| Method | Links | |
|---|---|---|
| FreoStreamGuardrail Type=Stream, Protected LLM=GPT-4o, Future-Aware Reasoning=true, Safety-Aligned Optimization=true2026.06 | 2.31 | |
| w/o Future-Aware ReasoningGuardrail Type=Stream, Protected LLM=GPT-4o, Future-Aware Reasoning=false, Safety-Aligned Optimization=true2026.06 | 2.31 | |
| Qwen-Gen-0.6B Prompt+ResponseGuardrail Type=Generative, Input Context=Prompt+Response, Protected LLM=GPT-4o2026.06 | 2.69 | |
| GuardReasoner-1BGuardrail Type=Generative, Protected LLM=GPT-4o2026.06 | 3.33 | |
| Qwen-Stream-0.6BGuardrail Type=Stream, Protected LLM=GPT-4o2026.06 | 4.03 | |
| w/o Safety-Aligned OptimizationGuardrail Type=Stream, Protected LLM=GPT-4o, Future-Aware Reasoning=true, Safety-Aligned Optimization=false2026.06 | 4.03 | |
| Nemotron-4BGuardrail Type=Generative, Protected LLM=GPT-4o2026.06 | 12.08 | |
| YuFeng-XGuard-0.6B Prompt+ResponseGuardrail Type=Generative, Input Context=Prompt+Response, Protected LLM=GPT-4o2026.06 | 14.87 | |
| YuFeng-XGuard-0.6B Prompt OnlyGuardrail Type=Generative, Input Context=Prompt Only, Protected LLM=GPT-4o2026.06 | 23.08 | |
| Qwen-Stream-8BGuardrail Type=Stream, Protected LLM=GPT-4o2026.06 | 24.88 | |
| Qwen-Gen-0.6B Prompt OnlyGuardrail Type=Generative, Input Context=Prompt Only, Protected LLM=GPT-4o2026.06 | 42.69 |