List your company

Persona Manipulation on MPI (test)

83.54Success ScorePHISH
-3.341619.214241.7764.3258Jan 23, 2026

Evaluation results

MethodLinks
PHISHModel=DeepSeek-V3, Category=Open2026.0183.54
DANModel=DeepSeek-V3, Category=Open2026.0181.25
PHISHModel=GPT-4o, Category=Proprietary2026.0179.38
FlipAttackModel=GPT-4o, Category=Proprietary2026.0178.54
PHISHModel=Gemini-2.0-Flash, Category=Proprietary2026.0175.42
DrAttackModel=Claude-3.5-Haiku, Category=Proprietary2026.0175
DANModel=Llama4-Maverick, Category=Open2026.0175
PHISHModel=Claude-3.5-Haiku, Category=Proprietary2026.0174.58
DrAttackModel=o3-mini, Category=Proprietary2026.0172.51
FlipAttackModel=o3-mini, Category=Proprietary2026.0170.63
CipherCHATModel=o3-mini, Category=Proprietary2026.0170.42
DrAttackModel=GPT-4o, Category=Proprietary2026.0170.21
FlipAttackModel=Llama4-Maverick, Category=Open2026.0168.75
PHISHModel=Llama4-Maverick, Category=Open2026.0168.13
PHISHModel=o3-mini, Category=Proprietary2026.0167.08
PHISHModel=MedGemma-27B (Medical), Category=Open2026.0166.67
DrAttackModel=DeepSeek-V3, Category=Open2026.0166.46
DrAttackModel=Llama4-Maverick, Category=Open2026.0166.04
DeepIncModel=o3-mini, Category=Proprietary2026.0165.42
DANModel=MedGemma-27B (Medical), Category=Open2026.0165.33
DANModel=o3-mini, Category=Proprietary2026.0159.38
DANModel=Gemini-2.0-Flash, Category=Proprietary2026.0157.29
FlipAttackModel=Claude-3.5-Haiku, Category=Proprietary2026.0156.46
DeepIncModel=Claude-3.5-Haiku, Category=Proprietary2026.0156.25
DeepIncModel=DeepSeek-V3, Category=Open2026.0156.25
DrAttackModel=Gemini-2.0-Flash, Category=Proprietary2026.0155.83
DeepIncModel=Llama4-Maverick, Category=Open2026.0153.54
DeepIncModel=GPT-4o, Category=Proprietary2026.0152.08
DrAttackModel=MedGemma-27B (Medical), Category=Open2026.0150.83
FlipAttackModel=DeepSeek-V3, Category=Open2026.0149.38
CipherCHATModel=Claude-3.5-Haiku, Category=Proprietary2026.0145.83
FlipAttackModel=ChatHaruhi (Role-playing), Category=Open2026.0143.96
CipherCHATModel=Gemini-2.0-Flash, Category=Proprietary2026.0142.92
FlipAttackModel=Gemini-2.0-Flash, Category=Proprietary2026.0142.71
CipherCHATModel=DeepSeek-V3, Category=Open2026.0142.71
DeepIncModel=MedGemma-27B (Medical), Category=Open2026.0141.67
DeepIncModel=Gemini-2.0-Flash, Category=Proprietary2026.0138.96
SLIPModel=Claude-3.5-Haiku, Category=Proprietary2026.0136.04
UASModel=MedGemma-27B (Medical), Category=Open2026.0135.83
DANModel=Claude-3.5-Haiku, Category=Proprietary2026.0134.58
UASModel=Gemini-2.0-Flash, Category=Proprietary2026.0130.42
PHISHModel=ChatHaruhi (Role-playing), Category=Open2026.0126.46
DANModel=ChatHaruhi (Role-playing), Category=Open2026.0126.04
UASModel=Llama4-Maverick, Category=Open2026.0125
CipherCHATModel=Llama4-Maverick, Category=Open2026.0124.79
DrAttackModel=ChatHaruhi (Role-playing), Category=Open2026.0124.38
DeepInceptionModel=ChatHaruhi (Role-playing), Category=Open2026.0123.75
CipherCHATModel=ChatHaruhi (Role-playing), Category=Open2026.0117.08
SLIPModel=Llama4-Maverick, Category=Open2026.0113.75
UASModel=ChatHaruhi (Role-playing), Category=Open2026.0112.08
SLIPModel=MedGemma-27B (Medical), Category=Open2026.0110.83
FlipAttackModel=MedGemma-27B (Medical), Category=Open2026.0110.83
SLIPModel=ChatHaruhi (Role-playing), Category=Open2026.017.92
RANDOMModel=Llama4-Maverick, Category=Open2026.017.08
UASModel=Claude-3.5-Haiku, Category=Proprietary2026.016.67
RANDOMModel=Claude-3.5-Haiku, Category=Proprietary2026.015.83
CipherCHATModel=GPT-4o, Category=Proprietary2026.015
RANDOMModel=Gemini-2.0-Flash, Category=Proprietary2026.014.17
RANDOMModel=ChatHaruhi (Role-playing), Category=Open2026.013.13
SLIPModel=o3-mini, Category=Proprietary2026.012.92
CipherCHATModel=MedGemma-27B (Medical), Category=Open2026.012.71
DANModel=GPT-4o, Category=Proprietary2026.012.29
SLIPModel=DeepSeek-V3, Category=Open2026.012.29
UASModel=DeepSeek-V3, Category=Open2026.011.67
RANDOMModel=o3-mini, Category=Proprietary2026.011.25
SLIPModel=GPT-4o, Category=Proprietary2026.010.83
UASModel=GPT-4o, Category=Proprietary2026.010.63
RANDOMModel=GPT-4o, Category=Proprietary2026.010.42
SLIPModel=Gemini-2.0-Flash, Category=Proprietary2026.010.42
RANDOMModel=MedGemma-27B (Medical), Category=Open2026.010.42
UASModel=o3-mini, Category=Proprietary2026.010
RANDOMModel=DeepSeek-V3, Category=Open2026.010