Meta Llama 4 Scout vs Alibaba Qwen 2.5 72B

Detailed comparison for LLMs

MetaAlibaba

On Guardion's LLM vulnerability Benchmark, Alibaba Qwen 2.5 72B is the more secure of the two: Llama 4 Scout scores 30.0% and Qwen 2.5 72B scores 26.3% on attack success rate (ASR) (lower is better).

Head-to-Head Overview

Qwen 2.5 72B is the overall winner in this comparison!

Attack Success Rate (lower is safer)

ASR for Meta Llama 4 Scout vs Alibaba Qwen 2.5 72B. Green marks the safer model on each metric.

Overall (ASR)

Llama 4 Scout
30.0%
Qwen 2.5 72B
26.3%

TAP Attack Method (ASR)

Llama 4 Scout
63.5%
Qwen 2.5 72B
55.2%

Crescendo Attack Method (ASR)

Llama 4 Scout
20.3%
Qwen 2.5 72B
23.7%

Zero-Shot (ASR)

Llama 4 Scout
6.1%
Qwen 2.5 72B
0.3%

Key Highlights

  • Alibaba Qwen 2.5 72B has a lower Overall (ASR).
  • Alibaba Qwen 2.5 72B has a lower TAP Attack Method (ASR).
  • Meta Llama 4 Scout 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.

OverallTAPCrescendoZero-Shot
Llama 4 Scout
Qwen 2.5 72B
Full security profile
Meta Llama 4 Scout
Full security profile
Alibaba Qwen 2.5 72B

Frequently asked questions

Is Meta Llama 4 Scout or Alibaba Qwen 2.5 72B more secure?

On Guardion's LLM vulnerability Benchmark, Alibaba Qwen 2.5 72B is the more secure of the two: Llama 4 Scout scores 30.0% and Qwen 2.5 72B scores 26.3% on attack success rate (ASR) (lower is better).

What is the attack success rate (ASR) of Llama 4 Scout vs Qwen 2.5 72B?

Llama 4 Scout has a 30.0% ASR and Qwen 2.5 72B has a 26.3% ASR — the share of adversarial prompts that succeed across zero-shot, TAP, and Crescendo attacks. Lower is safer.

How were Llama 4 Scout and Qwen 2.5 72B 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.

Related Comparisons