DeepSeek DeepSeek-V3.2 Thinking vs Meta Llama 3-7 DS
Detailed comparison for LLMs
DeepSeekMeta
Head-to-Head Overview
DeepSeek-V3.2 Thinking is the overall winner in this comparison!
LLM Metric
Comparison of Attack Success Rate (ASR) metrics for DeepSeek DeepSeek-V3.2 Thinking and Meta Llama 3-7 DS across the three attack methods.
Overall (ASR)
DeepSeek-V3.2 Thinking
0
Llama 3-7 DS
32.180
TAP Attack Method (ASR)
DeepSeek-V3.2 Thinking
0
Llama 3-7 DS
0
Crescendo Attack Method (ASR)
DeepSeek-V3.2 Thinking
0
Llama 3-7 DS
0
Zero-Shot (ASR)
DeepSeek-V3.2 Thinking
0
Llama 3-7 DS
10.540
Key Highlights
- DeepSeek DeepSeek-V3.2 Thinking has a lower Overall (ASR).
- DeepSeek DeepSeek-V3.2 Thinking has a lower Zero-Shot (ASR).
Metric Radar Chart
deepseek-v3-2-thinking
llama-3-7-ds