List your company

Excessive Response Induction on SecLens Multimodal (test)

64.31ASRSecLens
10.469224.447138.42552.4029Jun 14, 2025

Evaluation results

MethodLinks
SecLensModel=Pixtral-12b2025.0664.31
SecLensModel=Llama-NeXT2025.0663.29
SecLensModel=Qwen2.5-VL2025.0660.7
SecLensModel=Gemini 2.0-pro2025.0660.41
SecLensModel=Llama-OV-72b2025.0660.26
MCTSModel=Pixtral-12b2025.0659.78
SecLensModel=MiniCPM-o-2_62025.0659.41
SecLensModel=GPT-4-turbo2025.0658.13
MCTSModel=MiniCPM-o-2_62025.0657.56
SecLensModel=GPT-4o2025.0657.34
MCTSModel=Llama-OV-72b2025.0656.34
MCTSModel=Llama-NeXT2025.0656.31
MCTSModel=Qwen2.5-VL2025.0656.3
TuningModel=Pixtral-12b2025.0654.67
MCTSModel=Gemini 2.0-pro2025.0654.57
MCTSModel=GPT-4-turbo2025.0653.87
TuningModel=Llama-NeXT2025.0652.4
MCTSModel=GPT-4o2025.0652.1
SecLensModel=Claude-3.72025.0652.1
TuningModel=Llama-OV-72b2025.0651.14
TuningModel=Qwen2.5-VL2025.0650.54
TuningModel=Gemini 2.0-pro2025.0650.12
TuningModel=MiniCPM-o-2_62025.0649.83
MCTSModel=Claude-3.72025.0648.34
TuningModel=GPT-4-turbo2025.0643.15
TuningModel=GPT-4o2025.0642.31
TuningModel=Claude-3.72025.0640.12
RandomModel=Pixtral-12b2025.0621.47
RandomModel=Llama-NeXT2025.0619.84
RandomModel=Llama-OV-72b2025.0618.79
RandomModel=Qwen2.5-VL2025.0618.49
RandomModel=MiniCPM-o-2_62025.0618.24
RandomModel=GPT-4-turbo2025.0617.85
RandomModel=GPT-4o2025.0616.57
RandomModel=Gemini 2.0-pro2025.0616.48
RandomModel=Claude-3.72025.0612.54