Alibaba Qwen 2.5 72B vs OpenAI GPT-4o
Detailed comparison for LLMs
AlibabaOpenAI
Head-to-Head Overview
GPT-4o is the overall winner in this comparison!
LLM Metric
Comparison of Attack Success Rate (ASR) metrics for Alibaba Qwen 2.5 72B and OpenAI GPT-4o across the three attack methods.
Overall (ASR)
Qwen 2.5 72B
26.350
GPT-4o
22.840
TAP Attack Method (ASR)
Qwen 2.5 72B
55.160
GPT-4o
39.580
Crescendo Attack Method (ASR)
Qwen 2.5 72B
23.660
GPT-4o
25.560
Zero-Shot (ASR)
Qwen 2.5 72B
0.250
GPT-4o
3.390
Key Highlights
- OpenAI GPT-4o has a lower Overall (ASR).
- OpenAI GPT-4o has a lower TAP Attack Method (ASR).
- Alibaba Qwen 2.5 72B 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
gpt-4o