Anthropic Claude 3.5 Sonnet v1 vs DeepSeek DeepSeek R1 Distill Llama 8B
Detailed comparison for LLMs
AnthropicDeepSeek
Head-to-Head Overview
DeepSeek R1 Distill Llama 8B is the overall winner in this comparison!
LLM Metric
Comparison of Attack Success Rate (ASR) metrics for Anthropic Claude 3.5 Sonnet v1 and DeepSeek DeepSeek R1 Distill Llama 8B across the three attack methods.
Overall (ASR)
Claude 3.5 Sonnet v1
16.010
DeepSeek R1 Distill Llama 8B
0
TAP Attack Method (ASR)
Claude 3.5 Sonnet v1
28.390
DeepSeek R1 Distill Llama 8B
0
Crescendo Attack Method (ASR)
Claude 3.5 Sonnet v1
19.310
DeepSeek R1 Distill Llama 8B
0
Zero-Shot (ASR)
Claude 3.5 Sonnet v1
0.350
DeepSeek R1 Distill Llama 8B
0
Key Highlights
- DeepSeek DeepSeek R1 Distill Llama 8B has a lower Overall (ASR).
- DeepSeek DeepSeek R1 Distill Llama 8B has a lower TAP Attack Method (ASR).
- DeepSeek DeepSeek R1 Distill Llama 8B has a lower Crescendo Attack Method (ASR).
- DeepSeek DeepSeek R1 Distill Llama 8B has a lower Zero-Shot (ASR).
Metric Radar Chart
claude-3-5-sonnet-v1
deepseek-r1-distill-llama-8b