Alibaba Qwen2 7B Instruct vs Anthropic Claude 3.5 Sonnet v2
Detailed comparison for LLMs
AlibabaAnthropic
Head-to-Head Overview
Claude 3.5 Sonnet v2 is the overall winner in this comparison!
LLM Metric
Comparison of Attack Success Rate (ASR) metrics for Alibaba Qwen2 7B Instruct and Anthropic Claude 3.5 Sonnet v2 across the three attack methods.
Overall (ASR)
Qwen2 7B Instruct
100.000
Claude 3.5 Sonnet v2
4.390
TAP Attack Method (ASR)
Qwen2 7B Instruct
100.000
Claude 3.5 Sonnet v2
8.830
Crescendo Attack Method (ASR)
Qwen2 7B Instruct
100.000
Claude 3.5 Sonnet v2
3.810
Zero-Shot (ASR)
Qwen2 7B Instruct
100.000
Claude 3.5 Sonnet v2
0.540
Key Highlights
- Anthropic Claude 3.5 Sonnet v2 has a lower Overall (ASR).
- Anthropic Claude 3.5 Sonnet v2 has a lower TAP Attack Method (ASR).
- Anthropic Claude 3.5 Sonnet v2 has a lower Crescendo Attack Method (ASR).
- Anthropic Claude 3.5 Sonnet v2 has a lower Zero-Shot (ASR).
Metric Radar Chart
qwen2-7b-instruct
claude-3-5-sonnet-v2