Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Jailbreak Attack on MaliciousInstruct

100ASR

PiF

-2.9623.7750.577.23Dec 24, 2025Dec 31, 2025Jan 8, 2026Jan 16, 2026Jan 24, 2026Feb 1, 2026Feb 9, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2025.12
100----421
2025.12
100----299
2025.12
99----240
2025.12
99----318
2025.12
98----282
2025.12
96----248
2025.12
95----368
2026.01
94-----
2026.01
93-----
2026.01
91-----
2025.12
91----178
2026.01
87-----
2025.12
87----227
2026.01
86-----
2026.01
86-----
2026.02
84.3-----
2026.01
84-----
2025.12
84----181
2025.12
82----202
2026.02
81.8-----
2026.01
81-----
2026.01
73-----
2025.12
72----195
2025.12
70----214
2025.12
70----171
2026.01
63-----
2026.01
55-----
2025.12
54----140
2025.12
51----133
2026.01
43-----
2025.12
3----105
2025.12
3----106
2-----
2026.02
1-----
2026.02
1-----
2025.02
-2292973-