Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM Jailbreaking on R2D2
Loading...
31
SRF
Adaptive Probe-based Steering
0.84
8.67
16.5
24.33
May 19, 2026
SRF
HB
SR
Updated 13d ago
Evaluation Results
Method
Method
Links
SRF
HB
SR
Adaptive Probe-based Steering
2026.05
31
41
64
Angular
2026.05
25
35
50
RD-A
2026.05
23
31
45
RD-C
2026.05
18
25
39
RepE
2026.05
4
4
0
SCAV
2026.05
2
5
1
Feedback
Search any
task
Search any
task
