Detailed comparison for LLMs
It's a close match between DeepSeek R1 Distill Llama 8B and Gemini 2.0 Flash Thinking!
Comparison of Attack Success Rate (ASR) metrics for DeepSeek DeepSeek R1 Distill Llama 8B and Google Gemini 2.0 Flash Thinking across the three attack methods.
No specific highlights generated for this comparison.