List your company

Jailbreaking on HarmBench (test)

97ASR (GPT-4o)HMNS
35.53651.49367.4583.407Apr 11, 2026

Evaluation results

MethodLinks
HMNSTarget LLM=LLaMA-3.1-70B, Zero-shot=true2026.0497942——
HMNSTarget LLM=LLaMA-2-7B-Chat, Zero-shot=true2026.0496922.1——
ArrAttackTarget LLM=LLaMA-3.1-70B, Zero-shot=true2026.0491887.7——
ArrAttackTarget LLM=LLaMA-2-7B-Chat, Zero-shot=true2026.0490867.9——
HMNSTarget LLM=Phi-3-Medium-14B (Instruct), Zero-shot=true2026.0490842.1——
ArrAttackTarget LLM=Phi-3-Medium-14B (Instruct), Zero-shot=true2026.0484788.4——
TempestTarget LLM=LLaMA-3.1-70B, Zero-shot=true2026.0483.178.29.5——
TempestTarget LLM=LLaMA-2-7B-Chat, Zero-shot=true2026.048276.69.8——
TempestTarget LLM=Phi-3-Medium-14B (Instruct), Zero-shot=true2026.048073.910——
PrisonBreakTarget LLM=LLaMA-3.1-70B, Zero-shot=true2026.0475.670.211.9——
PrisonBreakTarget LLM=LLaMA-2-7B-Chat, Zero-shot=true2026.0474.168.312.1——
PrisonBreakTarget LLM=Phi-3-Medium-14B (Instruct), Zero-shot=true2026.047164.812.9——
AutoDANTarget LLM=LLaMA-3.1-70B, Zero-shot=true2026.0470.664.912.8——
AutoDANTarget LLM=LLaMA-2-7B-Chat, Zero-shot=true2026.0469.163.213.1——
MasterKeyTarget LLM=LLaMA-3.1-70B, Zero-shot=true2026.0468.963.410.8——
ADCTarget LLM=LLaMA-3.1-70B, Zero-shot=true2026.0467.461.910.1——
MasterKeyTarget LLM=LLaMA-2-7B-Chat, Zero-shot=true2026.046761.210.9——
ADCTarget LLM=LLaMA-2-7B-Chat, Zero-shot=true2026.0465.760.110.6——
Many-shot JB (MSJ)Target LLM=LLaMA-3.1-70B, Zero-shot=true2026.0463.758.411——
AutoDANTarget LLM=Phi-3-Medium-14B (Instruct), Zero-shot=true2026.0462.456.713.9——
Many-shot JB (MSJ)Target LLM=LLaMA-2-7B-Chat, Zero-shot=true2026.0462.256.711.4——
MasterKeyTarget LLM=Phi-3-Medium-14B (Instruct), Zero-shot=true2026.0460.154.211.7——
ADCTarget LLM=Phi-3-Medium-14B (Instruct), Zero-shot=true2026.0458.653.111.2——
Many-shot JB (MSJ)Target LLM=Phi-3-Medium-14B (Instruct), Zero-shot=true2026.0455.249.812.3——
Foot-In-The-Door (FITD)Target LLM=LLaMA-3.1-70B, Zero-shot=true2026.0443.838.416.2——
Foot-In-The-Door (FITD)Target LLM=LLaMA-2-7B-Chat, Zero-shot=true2026.0441.336.116.8——
Foot-In-The-Door (FITD)Target LLM=Phi-3-Medium-14B (Instruct), Zero-shot=true2026.0437.932.817.6——
BaselineModel=Llama-3.1-8B, Evaluation Denominator=/200, Sample Budget=N=2002026.05———37—
BaselineModel=Mistral-7B, Evaluation Denominator=/200, Sample Budget=N=2002026.05———35—
BaselineModel=Qwen2.5-7B, Evaluation Denominator=/200, Sample Budget=N=2002026.05———8—
BaselineModel=Qwen3-4B, Evaluation Denominator=/200, Sample Budget=N=2002026.05———8.5—
BaselineModel=Gemma-3-4B, Evaluation Denominator=/200, Sample Budget=N=2002026.05———14—
DPO bestModel=Llama-3.1-8B, Evaluation Denominator=/200, Sample Budget=N=2002026.05———35.520.5
DPO bestModel=Mistral-7B, Evaluation Denominator=/200, Sample Budget=N=2002026.05———2830.5
DPO bestModel=Qwen2.5-7B, Evaluation Denominator=/200, Sample Budget=N=2002026.05———7.513
DPO bestModel=Qwen3-4B, Evaluation Denominator=/200, Sample Budget=N=2002026.05———113.5
DPO bestModel=Gemma-3-4B, Evaluation Denominator=/200, Sample Budget=N=2002026.05———1822.5
SmoothLLMModel=Llama-3.1-8B, Evaluation Denominator=/nr, Sample Budget=N=2002026.05———5.6—
SmoothLLMModel=Llama-3.1-8B, Evaluation Denominator=/200, Sample Budget=N=2002026.05———15—
SmoothLLMModel=Mistral-7B, Evaluation Denominator=/nr, Sample Budget=N=2002026.05———20.2—
SmoothLLMModel=Mistral-7B, Evaluation Denominator=/200, Sample Budget=N=2002026.05———58.5—
SmoothLLMModel=Qwen2.5-7B, Evaluation Denominator=/nr, Sample Budget=N=2002026.05———5.4—
SmoothLLMModel=Qwen2.5-7B, Evaluation Denominator=/200, Sample Budget=N=2002026.05———20.5—
SmoothLLMModel=Qwen3-4B, Evaluation Denominator=/nr, Sample Budget=N=2002026.05———4.5—
SmoothLLMModel=Qwen3-4B, Evaluation Denominator=/200, Sample Budget=N=2002026.05———14.5—
SmoothLLMModel=Gemma-3-4B, Evaluation Denominator=/nr, Sample Budget=N=2002026.05———16.8—
SmoothLLMModel=Gemma-3-4B, Evaluation Denominator=/200, Sample Budget=N=2002026.05———40.5—