Anthropic Claude 3.7 Sonnet vs DeepSeek DeepSeek R1 Distill Llama 8B
Detailed comparison for LLMs
AnthropicDeepSeek
Head-to-Head Overview
Claude 3.7 Sonnet is the overall winner in this comparison!
LLM Metric
Comparison of Attack Success Rate (ASR) metrics for Anthropic Claude 3.7 Sonnet and DeepSeek DeepSeek R1 Distill Llama 8B across the three attack methods.
Overall (ASR)
Claude 3.7 Sonnet
20.280
DeepSeek R1 Distill Llama 8B
100.000
TAP Attack Method (ASR)
Claude 3.7 Sonnet
31.430
DeepSeek R1 Distill Llama 8B
100.000
Crescendo Attack Method (ASR)
Claude 3.7 Sonnet
25.270
DeepSeek R1 Distill Llama 8B
100.000
Zero-Shot (ASR)
Claude 3.7 Sonnet
0
DeepSeek R1 Distill Llama 8B
100.000
Key Highlights
- Anthropic Claude 3.7 Sonnet has a lower Overall (ASR).
- Anthropic Claude 3.7 Sonnet has a lower TAP Attack Method (ASR).
- Anthropic Claude 3.7 Sonnet has a lower Crescendo Attack Method (ASR).
Metric Radar Chart
claude-3-7-sonnet
deepseek-r1-distill-llama-8b