Alibaba Qwen 2.5 72B vs Anthropic Claude 4.0 Sonnet
Detailed comparison for LLMs
AlibabaAnthropic
Head-to-Head Overview
Claude 4.0 Sonnet is the overall winner in this comparison!
LLM Metric
Comparison of Attack Success Rate (ASR) metrics for Alibaba Qwen 2.5 72B and Anthropic Claude 4.0 Sonnet across the three attack methods.
Overall (ASR)
Qwen 2.5 72B
26.350
Claude 4.0 Sonnet
13.630
TAP Attack Method (ASR)
Qwen 2.5 72B
55.160
Claude 4.0 Sonnet
22.020
Crescendo Attack Method (ASR)
Qwen 2.5 72B
23.660
Claude 4.0 Sonnet
14.790
Zero-Shot (ASR)
Qwen 2.5 72B
0.250
Claude 4.0 Sonnet
4.080
Key Highlights
- Anthropic Claude 4.0 Sonnet has a lower Overall (ASR).
- Anthropic Claude 4.0 Sonnet has a lower TAP Attack Method (ASR).
- Anthropic Claude 4.0 Sonnet has a lower Crescendo Attack Method (ASR).
- Alibaba Qwen 2.5 72B has a lower Zero-Shot (ASR).
Metric Radar Chart
qwen-2-5-72b
claude-4-0-sonnet