Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM Red-teaming on Jailbreak R1-defended Target Model
Loading...
87.67
UA
S-GFN
-3.5068
20.1641
43.835
67.5059
May 1, 2026
UA
ASR
Updated 1mo ago
Evaluation Results
Method
Method
Links
UA
ASR
S-GFN
2026.05
87.67
56.25
GFN
2026.05
7.67
19.86
ICL
2026.05
7.33
0.72
Rainbow Teaming
2026.05
4.67
0.46
Jailbreak R1
CoT=enabled
2026.05
2.67
0.26
PPO + Curiosity
2026.05
0.33
0.03
SFT
2026.05
0
0
DPO
2026.05
0
0
PPO
2026.05
0
0
Feedback
Search any
task
Search any
task