Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Jailbreak Attack Success Rate on AdvBench Phi-3 Medium 14B Instruct
Loading...
41
ASR (SMO, GPT-4o)
HMNS
6.68
15.59
24.5
33.41
Apr 11, 2026
ASR (SMO, GPT-4o)
ASR (SMO, GPT-5)
ASR (DPP, GPT-4o)
ASR (DPP, GPT-5)
ASR (RPO, GPT-4o)
ASR (RPO, GPT-5)
ASR (PAR, GPT-4o)
ASR (PAR, GPT-5)
ASR (PAT, GPT-4o)
ASR (PAT, GPT-5)
ASR (SAF, GPT-4o)
ASR (SAF, GPT-5)
ASR Avg (GPT-4o)
ASR Avg (GPT-5)
Updated 5d ago
Evaluation Results
Method
Method
Links
ASR (SMO, GPT-4o)
ASR (SMO, GPT-5)
ASR (DPP, GPT-4o)
ASR (DPP, GPT-5)
ASR (RPO, GPT-4o)
ASR (RPO, GPT-5)
ASR (PAR, GPT-4o)
ASR (PAR, GPT-5)
ASR (PAT, GPT-4o)
ASR (PAT, GPT-5)
ASR (SAF, GPT-4o)
ASR (SAF, GPT-5)
ASR Avg (GPT-4o)
ASR Avg (GPT-5)
HMNS
2026.04
41
27
55
42
84
63
66
47
50
35
48
36
57.3
41.7
ArrAttack
2026.04
36
24
50
38
76
57
60
42
44
31
41
30
51.2
37
Tempest
2026.04
25
19
40
29
69
51
50
37
35
24
32
23
41.8
30.5
AutoDAN
2026.04
12
9
22
16
36
27
26
19
20
15
16
12
22
16.3
FITD
2026.04
8
6
10
8
18
13
12
9
10
7
9
7
11.2
8.3
Feedback
Search any
task
Search any
task