Alibaba Qwen 2.5 72B: LLM Security & Jailbreak Resistance
As of 2026-07-04, Alibaba Qwen 2.5 72B has an attack success rate (ASR) of 26.3% on Guardion's LLM Vulnerability benchmark — ranking #28 of 93 models. It is moderately resistant — a meaningful share of adversarial prompts succeed.
Attack Success Rate (ASR) is the share of adversarial prompts that elicit harmful output across zero-shot, TAP, and Crescendo attacks (HarmBench framework). Lower is safer. "Est." models are calibrated from public safety evaluations pending a Guardion benchmark run.
How Qwen 2.5 72B compares
Frequently asked questions
How secure is Alibaba Qwen 2.5 72B against jailbreaks?
Alibaba Qwen 2.5 72B is moderately resistant — a meaningful share of adversarial prompts succeed. On Guardion's LLM Vulnerability benchmark it records a 26.3% attack success rate (73.7% robustness), ranking #28 of 93 models.
What is Qwen 2.5 72B's attack success rate (ASR)?
Qwen 2.5 72B's overall ASR is 26.3% — the share of adversarial prompts that elicit harmful output across zero-shot, TAP, and Crescendo attacks. Lower is safer.
Is Qwen 2.5 72B more secure than Qwen3-Max?
Qwen 2.5 72B is more robust: 26.3% ASR vs Qwen3-Max's 28.0%. See the full head-to-head comparison for the per-attack breakdown.
How can I make Qwen 2.5 72B safer to deploy?
Even robust models are bypassed under sustained attack. An inline runtime guardrail that classifies prompts and responses — like Guardion's prompt-defense models — blocks jailbreaks and prompt injection before they reach Qwen 2.5 72B.
Harden Qwen 2.5 72B in production
Guardion's runtime guardrails block jailbreaks and prompt injection before they reach any model — with sub-130ms policy decisions.
Request a demo