Alibaba Qwen 2.5 72B vs OpenAI GPT OSS 20B
Detailed comparison for LLMs
On Guardion's LLM vulnerability Benchmark, OpenAI GPT OSS 20B is the more secure of the two: Qwen 2.5 72B scores 26.3% and GPT OSS 20B scores 20.0% on attack success rate (ASR) (lower is better). One or both scores are estimated from public safety evaluations pending a Guardion benchmark run.
Head-to-Head Overview
GPT OSS 20B is the overall winner in this comparison!
Attack Success Rate (lower is safer)
ASR for Alibaba Qwen 2.5 72B vs OpenAI GPT OSS 20B. Green marks the safer model on each metric. Only the overall score is available for estimated models.
Overall (ASR)
TAP Attack Method (ASR)
Crescendo Attack Method (ASR)
Zero-Shot (ASR)
Key Highlights
- OpenAI GPT OSS 20B has a lower Overall (ASR).
- Alibaba Qwen 2.5 72B 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).
Security Profile
Outward is better on every axis.
Frequently asked questions
Is Alibaba Qwen 2.5 72B or OpenAI GPT OSS 20B more secure?
On Guardion's LLM vulnerability Benchmark, OpenAI GPT OSS 20B is the more secure of the two: Qwen 2.5 72B scores 26.3% and GPT OSS 20B scores 20.0% on attack success rate (ASR) (lower is better). One or both scores are estimated from public safety evaluations pending a Guardion benchmark run.
What is the attack success rate (ASR) of Qwen 2.5 72B vs GPT OSS 20B?
Qwen 2.5 72B has a 26.3% ASR and GPT OSS 20B has a 20.0% ASR — the share of adversarial prompts that succeed across zero-shot, TAP, and Crescendo attacks. Lower is safer.
How were Qwen 2.5 72B and GPT OSS 20B tested?
Both were red-teamed with the HarmBench framework across zero-shot, TAP (Tree of Attacks with Pruning), and Crescendo multi-turn attacks, scored by Attack Success Rate.