List your company

Persona Manipulation on ANTHR (test)

91.04Success ScoreDAN
-3.641620.939245.5270.1008Jan 23, 2026

Evaluation results

MethodLinks
DANModel=DeepSeek-V3, Category=Open2026.0191.04
PHISHModel=DeepSeek-V3, Category=Open2026.0189.38
DrAttackModel=Claude-3.5-Haiku, Category=Proprietary2026.0188.33
CipherCHATModel=o3-mini, Category=Proprietary2026.0187.08
DrAttackModel=o3-mini, Category=Proprietary2026.0186.88
FlipAttackModel=o3-mini, Category=Proprietary2026.0185.83
FlipAttackModel=GPT-4o, Category=Proprietary2026.0185
PHISHModel=Claude-3.5-Haiku, Category=Proprietary2026.0184.33
DrAttackModel=GPT-4o, Category=Proprietary2026.0183.33
DANModel=Llama4-Maverick, Category=Open2026.0181.88
DrAttackModel=DeepSeek-V3, Category=Open2026.0181.04
CipherCHATModel=Claude-3.5-Haiku, Category=Proprietary2026.0178.13
PHISHModel=GPT-4o, Category=Proprietary2026.0176.67
DeepIncModel=o3-mini, Category=Proprietary2026.0176.04
FlipAttackModel=Claude-3.5-Haiku, Category=Proprietary2026.0174.79
PHISHModel=o3-mini, Category=Proprietary2026.0173.13
DrAttackModel=Llama4-Maverick, Category=Open2026.0173.13
FlipAttackModel=Llama4-Maverick, Category=Open2026.0172.29
DeepIncModel=Claude-3.5-Haiku, Category=Proprietary2026.0171.87
PHISHModel=Gemini-2.0-Flash, Category=Proprietary2026.0171.04
PHISHModel=MedGemma-27B (Medical), Category=Open2026.0169.79
DANModel=MedGemma-27B (Medical), Category=Open2026.0168.96
DeepIncModel=DeepSeek-V3, Category=Open2026.0168.13
FlipAttackModel=DeepSeek-V3, Category=Open2026.0165.83
DeepIncModel=GPT-4o, Category=Proprietary2026.0164.79
DANModel=o3-mini, Category=Proprietary2026.0162.71
DrAttackModel=MedGemma-27B (Medical), Category=Open2026.0162.71
DrAttackModel=Gemini-2.0-Flash, Category=Proprietary2026.0158.13
FlipAttackModel=ChatHaruhi (Role-playing), Category=Open2026.0153.75
DANModel=Gemini-2.0-Flash, Category=Proprietary2026.0152.29
PHISHModel=Llama4-Maverick, Category=Open2026.0152.29
DeepIncModel=Llama4-Maverick, Category=Open2026.0150.21
CipherCHATModel=DeepSeek-V3, Category=Open2026.0144.38
FlipAttackModel=Gemini-2.0-Flash, Category=Proprietary2026.0142.29
DANModel=Claude-3.5-Haiku, Category=Proprietary2026.0141.88
SLIPModel=Claude-3.5-Haiku, Category=Proprietary2026.0138.75
UASModel=MedGemma-27B (Medical), Category=Open2026.0136.46
DeepIncModel=MedGemma-27B (Medical), Category=Open2026.0135.63
DANModel=ChatHaruhi (Role-playing), Category=Open2026.0132.92
CipherCHATModel=Llama4-Maverick, Category=Open2026.0132.5
UASModel=Gemini-2.0-Flash, Category=Proprietary2026.0130.83
DeepIncModel=Gemini-2.0-Flash, Category=Proprietary2026.0129.17
CipherCHATModel=Gemini-2.0-Flash, Category=Proprietary2026.0127.71
UASModel=Llama4-Maverick, Category=Open2026.0123.33
PHISHModel=ChatHaruhi (Role-playing), Category=Open2026.0123.33
DrAttackModel=ChatHaruhi (Role-playing), Category=Open2026.0122.33
CipherCHATModel=ChatHaruhi (Role-playing), Category=Open2026.0120.62
DeepInceptionModel=ChatHaruhi (Role-playing), Category=Open2026.0113.96
SLIPModel=Llama4-Maverick, Category=Open2026.0113.75
SLIPModel=DeepSeek-V3, Category=Open2026.0110.21
CipherCHATModel=GPT-4o, Category=Proprietary2026.019.38
FlipAttackModel=MedGemma-27B (Medical), Category=Open2026.017.5
SLIPModel=MedGemma-27B (Medical), Category=Open2026.015.63
RANDOMModel=Llama4-Maverick, Category=Open2026.015
UASModel=ChatHaruhi (Role-playing), Category=Open2026.013.13
UASModel=Claude-3.5-Haiku, Category=Proprietary2026.012.92
RANDOMModel=Claude-3.5-Haiku, Category=Proprietary2026.012.71
CipherCHATModel=MedGemma-27B (Medical), Category=Open2026.012.71
RANDOMModel=GPT-4o, Category=Proprietary2026.012.5
RANDOMModel=Gemini-2.0-Flash, Category=Proprietary2026.012.5
SLIPModel=ChatHaruhi (Role-playing), Category=Open2026.011.25
UASModel=GPT-4o, Category=Proprietary2026.011.04
RANDOMModel=o3-mini, Category=Proprietary2026.011.04
RANDOMModel=ChatHaruhi (Role-playing), Category=Open2026.011.04
SLIPModel=Gemini-2.0-Flash, Category=Proprietary2026.010.83
SLIPModel=o3-mini, Category=Proprietary2026.010.83
SLIPModel=GPT-4o, Category=Proprietary2026.010.63
UASModel=DeepSeek-V3, Category=Open2026.010.63
RANDOMModel=DeepSeek-V3, Category=Open2026.010.21
DANModel=GPT-4o, Category=Proprietary2026.010
UASModel=o3-mini, Category=Proprietary2026.010
RANDOMModel=MedGemma-27B (Medical), Category=Open2026.010