DeepSeek DeepSeek-V3.2 Thinking vs OpenAI GPT-4o Mini
Detailed comparison for LLMs
DeepSeekOpenAI
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 OpenAI GPT-4o Mini across the three attack methods.
Overall (ASR)
DeepSeek-V3.2 Thinking
0
GPT-4o Mini
26.670
TAP Attack Method (ASR)
DeepSeek-V3.2 Thinking
0
GPT-4o Mini
40.500
Crescendo Attack Method (ASR)
DeepSeek-V3.2 Thinking
0
GPT-4o Mini
33.100
Zero-Shot (ASR)
DeepSeek-V3.2 Thinking
0
GPT-4o Mini
6.410
Key Highlights
- DeepSeek DeepSeek-V3.2 Thinking has a lower Overall (ASR).
- DeepSeek DeepSeek-V3.2 Thinking has a lower TAP Attack Method (ASR).
- DeepSeek DeepSeek-V3.2 Thinking has a lower Crescendo Attack Method (ASR).
- DeepSeek DeepSeek-V3.2 Thinking has a lower Zero-Shot (ASR).
Metric Radar Chart
deepseek-v3-2-thinking
gpt-4o-mini