Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Persona Manipulation on BFI (test)

95.58Success Score

PHISH

-3.823221.983447.7973.5966Jan 23, 2026
Updated 3mo ago

Evaluation Results

MethodLinks
2026.01
95.58
2026.01
92.46
2026.01
91.31
2026.01
90.68
2026.01
90.61
2026.01
89.94
2026.01
89.9
2026.01
88.22
2026.01
87.44
2026.01
82.28
2026.01
82.2
2026.01
80.63
2026.01
79.31
2026.01
76.72
2026.01
76.38
2026.01
73.82
2026.01
73.51
2026.01
72.08
2026.01
71.89
2026.01
70.83
2026.01
70.56
2026.01
70
2026.01
69.78
2026.01
68.1
2026.01
67.46
2026.01
67.15
2026.01
61.83
2026.01
56.43
2026.01
54.26
2026.01
51.83
2026.01
48.42
2026.01
47.94
2026.01
47.33
2026.01
44.97
2026.01
44.5
2026.01
39.89
2026.01
37.67
2026.01
37.36
2026.01
37.22
2026.01
36.74
2026.01
36.35
2026.01
36.31
2026.01
34.65
2026.01
32.47
2026.01
32.28
2026.01
31.78
2026.01
30.14
2026.01
28.88
2026.01
22.9
2026.01
17.17
2026.01
14.56
2026.01
13.33
2026.01
12.19
2026.01
11.56
2026.01
9.43
2026.01
6.89
2026.01
5.42
2026.01
4.86
2026.01
4.44
2026.01
3.36
2026.01
3.28
2026.01
2.78
2026.01
2.78
2026.01
1.81
2026.01
1.74
2026.01
1.67
2026.01
1.63
2026.01
1.18
2026.01
1.11
2026.01
0.56
2026.01
0
2026.01
0