List your company

Speculative Advice Induction on SecLens Multimodal (test)

63.19ASR (%)SecLens
6.125220.940135.75550.5699Jun 14, 2025

Evaluation results

MethodLinks
SecLensModel=Pixtral-12b2025.0663.19
SecLensModel=Llama-NeXT2025.0660.45
SecLensModel=MiniCPM-o-2_62025.0658.21
SecLensModel=Gemini 2.0-pro2025.0658.2
MCTSModel=Pixtral-12b2025.0657.27
SecLensModel=Llama-OV-72b2025.0657.25
MCTSModel=Llama-NeXT2025.0656.67
SecLensModel=Qwen2.5-VL2025.0655.45
MCTSModel=Gemini 2.0-pro2025.0655.16
MCTSModel=MiniCPM-o-2_62025.0653.72
MCTSModel=Llama-OV-72b2025.0653.31
TuningModel=Pixtral-12b2025.0652.89
SecLensModel=GPT-4o2025.0652.14
MCTSModel=Qwen2.5-VL2025.0652.13
TuningModel=Llama-NeXT2025.0651.25
SecLensModel=GPT-4-turbo2025.0650.78
TuningModel=MiniCPM-o-2_62025.0650.64
MCTSModel=GPT-4o2025.0649.72
TuningModel=Llama-OV-72b2025.0648.45
TuningModel=Gemini 2.0-pro2025.0647.82
MCTSModel=GPT-4-turbo2025.0646.56
SecLensModel=Claude-3.72025.0646.54
TuningModel=Qwen2.5-VL2025.0644.46
MCTSModel=Claude-3.72025.0641.35
TuningModel=GPT-4o2025.0640.47
TuningModel=GPT-4-turbo2025.0635.32
TuningModel=Claude-3.72025.0634.32
RandomModel=Pixtral-12b2025.0620.56
RandomModel=Qwen2.5-VL2025.0617.26
RandomModel=Llama-NeXT2025.0616.48
RandomModel=Llama-OV-72b2025.0615.98
RandomModel=GPT-4-turbo2025.0615.47
RandomModel=MiniCPM-o-2_62025.0615.29
RandomModel=GPT-4o2025.0614.84
RandomModel=Gemini 2.0-pro2025.0613.38
RandomModel=Claude-3.72025.068.32