Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Jailbreak Defense Evaluation on EMRA JQ
Loading...
1
Attack Success Rate (ASR)
GoalPriority
-0.208
7.946
16.1
24.254
Apr 5, 2026
Attack Success Rate (ASR)
Updated 12d ago
Evaluation Results
Method
Method
Links
Attack Success Rate (ASR)
GoalPriority
Target LLM=GPT-5
2026.04
1
CoopGuard
Target LLM=GPT-5
2026.04
1
GoalPriority
Target LLM=Gemini-2.5-Pro
2026.04
1
Self-Reminder
Target LLM=GPT-5
2026.04
1.8
RPO
Target LLM=GPT-5
2026.04
2.3
CoopGuard
Target LLM=Gemini-2.5-Pro
2026.04
2.3
PAT
Target LLM=GPT-5
2026.04
2.7
CoopGuard
Target LLM=DeepSeek-V3
2026.04
4.2
Self-Reminder
Target LLM=Gemini-2.5-Pro
2026.04
5.1
GoalPriority
Target LLM=DeepSeek-V3
2026.04
5.3
Self-Reminder
Target LLM=DeepSeek-V3
2026.04
12.6
SecurityLingua
Target LLM=DeepSeek-V3
2026.04
17.4
SecurityLingua
Target LLM=Gemini-2.5-Pro
2026.04
21
RPO
Target LLM=Gemini-2.5-Pro
2026.04
21.1
PAT
Target LLM=Gemini-2.5-Pro
2026.04
26.4
SecurityLingua
Target LLM=GPT-5
2026.04
28.3
PAT
Target LLM=DeepSeek-V3
2026.04
28.3
RPO
Target LLM=DeepSeek-V3
2026.04
31.2
Feedback
Search any
task
Search any
task