Deepseek Deepseek R1 vs Mistral Mistral 8x22B

Detailed comparison for LLMs

DeepseekMistral

On Guardion's LLM vulnerability Benchmark, Mistral Mistral 8x22B is the more secure of the two: Deepseek R1 scores 42.6% and Mistral 8x22B scores 31.5% on attack success rate (ASR) (lower is better).

Head-to-Head Overview

Mistral 8x22B is the overall winner in this comparison!

Attack Success Rate (lower is safer)

ASR for Deepseek Deepseek R1 vs Mistral Mistral 8x22B. Green marks the safer model on each metric.

Overall (ASR)

Deepseek R1
42.6%
Mistral 8x22B
31.5%

TAP Attack Method (ASR)

Deepseek R1
76.9%
Mistral 8x22B

Crescendo Attack Method (ASR)

Deepseek R1
34.8%
Mistral 8x22B

Zero-Shot (ASR)

Deepseek R1
16.1%
Mistral 8x22B
12.2%

Key Highlights

  • Mistral Mistral 8x22B has a lower Overall (ASR).
  • Mistral Mistral 8x22B has a lower Zero-Shot (ASR).

Security Profile

Outward is better on every axis.

OverallTAPCrescendoZero-Shot
Deepseek R1
Mistral 8x22B
Full security profile
Deepseek Deepseek R1
Full security profile
Mistral Mistral 8x22B

Frequently asked questions

Is Deepseek Deepseek R1 or Mistral Mistral 8x22B more secure?

On Guardion's LLM vulnerability Benchmark, Mistral Mistral 8x22B is the more secure of the two: Deepseek R1 scores 42.6% and Mistral 8x22B scores 31.5% on attack success rate (ASR) (lower is better).

What is the attack success rate (ASR) of Deepseek R1 vs Mistral 8x22B?

Deepseek R1 has a 42.6% ASR and Mistral 8x22B has a 31.5% ASR — the share of adversarial prompts that succeed across zero-shot, TAP, and Crescendo attacks. Lower is safer.

How were Deepseek R1 and Mistral 8x22B 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