List your company

Jailbreak Attack on AdvBench (Avg.Q)

93.48Avg.QTAP
-2.574422.362847.372.2372Feb 26, 2026

Evaluation results

MethodLinks
TAPTarget LLM=Claude-3.72026.0293.48
TAPTarget LLM=Gemini-2.5-flash2026.0293.14
TAPTarget LLM=Qwen3-235b2026.0290.42
TAPTarget LLM=Deepseek-Reasoner2026.0286.44
GPTFUZZERTarget LLM=GPT-4o2026.0277.26
TAPTarget LLM=GPT-4o2026.0265.72
PAIRTarget LLM=Gemini-2.5-flash2026.0260
PAIRTarget LLM=GPT-4o2026.0257.36
PAIRTarget LLM=Qwen3-235b2026.0257
GPTFUZZERTarget LLM=Gemini-2.5-flash2026.0256.96
TAPTarget LLM=Grok-32026.0253.96
PAIRTarget LLM=Grok-32026.0251.36
PAIRTarget LLM=Claude-3.72026.0251.12
PAIRTarget LLM=Deepseek-Reasoner2026.0240.32
GPTFUZZERTarget LLM=Claude-3.72026.0232.62
CL-GSOTarget LLM=Claude-3.72026.0221.42
GPTFUZZERTarget LLM=Qwen3-235b2026.0219.08
AutoDAN-turbo-RTarget LLM=GPT-4o2026.0216.84
AutoDAN-turbo-RTarget LLM=Claude-3.72026.0214.8
AutoDAN-turbo-RTarget LLM=Grok-32026.0213.58
AutoDAN-turbo-RTarget LLM=Qwen3-235b2026.0213.48
AutoDAN-turbo-RTarget LLM=Deepseek-Reasoner2026.0210.62
AutoDAN-turbo-RTarget LLM=Gemini-2.5-flash2026.0210
GPTFUZZERTarget LLM=Deepseek-Reasoner2026.025.98
CL-GSOTarget LLM=Qwen3-235b2026.025.06
CL-GSOTarget LLM=GPT-4o2026.024
CL-GSOTarget LLM=Gemini-2.5-flash2026.023.62
CL-GSOTarget LLM=Deepseek-Reasoner2026.023.26
CC-BOSTarget LLM=Claude-3.72026.022.38
CC-BOSTarget LLM=Qwen3-235b2026.021.54
CC-BOSTarget LLM=Gemini-2.5-flash2026.021.46
GPTFUZZERTarget LLM=Grok-32026.021.32
CC-BOSTarget LLM=GPT-4o2026.021.28
CL-GSOTarget LLM=Grok-32026.021.24
CC-BOSTarget LLM=Grok-32026.021.18
CC-BOSTarget LLM=Deepseek-Reasoner2026.021.12