Mistral Ministral 3 8B Base 2512 vs Mistral Mixtral 8x7B

Detailed comparison for LLMs

MistralMistral

On Guardion's LLM vulnerability Benchmark, Mistral Mixtral 8x7B is the more secure of the two: Ministral 3 8B Base 2512 scores 55.0% and Mixtral 8x7B scores 38.0% 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

Mixtral 8x7B is the overall winner in this comparison!

Attack Success Rate (lower is safer)

ASR for Mistral Ministral 3 8B Base 2512 vs Mistral Mixtral 8x7B. Green marks the safer model on each metric. Only the overall score is available for estimated models.

Overall (ASR)

Ministral 3 8B Base 2512
55.0%
Mixtral 8x7B
38.0%

TAP Attack Method (ASR)

Ministral 3 8B Base 2512
100.0%
Mixtral 8x7B
66.2%

Crescendo Attack Method (ASR)

Ministral 3 8B Base 2512
100.0%
Mixtral 8x7B
24.3%

Zero-Shot (ASR)

Ministral 3 8B Base 2512
100.0%
Mixtral 8x7B
23.6%

Key Highlights

  • Mistral Mixtral 8x7B has a lower Overall (ASR).
  • Mistral Mixtral 8x7B has a lower TAP Attack Method (ASR).
  • Mistral Mixtral 8x7B has a lower Crescendo Attack Method (ASR).
  • Mistral Mixtral 8x7B has a lower Zero-Shot (ASR).

Security Profile

Outward is better on every axis.

OverallTAPCrescendoZero-Shot
Ministral 3 8B Base 2512
Mixtral 8x7B
Full security profile
Mistral Ministral 3 8B Base 2512
Full security profile
Mistral Mixtral 8x7B

Frequently asked questions

Is Mistral Ministral 3 8B Base 2512 or Mistral Mixtral 8x7B more secure?

On Guardion's LLM vulnerability Benchmark, Mistral Mixtral 8x7B is the more secure of the two: Ministral 3 8B Base 2512 scores 55.0% and Mixtral 8x7B scores 38.0% 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 Ministral 3 8B Base 2512 vs Mixtral 8x7B?

Ministral 3 8B Base 2512 has a 55.0% ASR and Mixtral 8x7B has a 38.0% ASR — the share of adversarial prompts that succeed across zero-shot, TAP, and Crescendo attacks. Lower is safer.

How were Ministral 3 8B Base 2512 and Mixtral 8x7B 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