Mistral Ministral 3 3B Base 2512 vs Mistral Mistral NeMo Instruct

Detailed comparison for LLMs

MistralMistral

On Guardion's LLM vulnerability Benchmark, Mistral Mistral NeMo Instruct is the more secure of the two: Ministral 3 3B Base 2512 scores 62.0% and Mistral NeMo Instruct scores 50.0% 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

Mistral NeMo Instruct is the overall winner in this comparison!

Attack Success Rate (lower is safer)

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

Overall (ASR)

Ministral 3 3B Base 2512
62.0%
Mistral NeMo Instruct
50.0%

TAP Attack Method (ASR)

Ministral 3 3B Base 2512
100.0%
Mistral NeMo Instruct
100.0%

Crescendo Attack Method (ASR)

Ministral 3 3B Base 2512
100.0%
Mistral NeMo Instruct
100.0%

Zero-Shot (ASR)

Ministral 3 3B Base 2512
100.0%
Mistral NeMo Instruct
100.0%

Key Highlights

  • Mistral Mistral NeMo Instruct has a lower Overall (ASR).

Security Profile

Outward is better on every axis.

OverallTAPCrescendoZero-Shot
Ministral 3 3B Base 2512
Mistral NeMo Instruct
Full security profile
Mistral Ministral 3 3B Base 2512
Full security profile
Mistral Mistral NeMo Instruct

Frequently asked questions

Is Mistral Ministral 3 3B Base 2512 or Mistral Mistral NeMo Instruct more secure?

On Guardion's LLM vulnerability Benchmark, Mistral Mistral NeMo Instruct is the more secure of the two: Ministral 3 3B Base 2512 scores 62.0% and Mistral NeMo Instruct scores 50.0% 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 3B Base 2512 vs Mistral NeMo Instruct?

Ministral 3 3B Base 2512 has a 62.0% ASR and Mistral NeMo Instruct has a 50.0% ASR — the share of adversarial prompts that succeed across zero-shot, TAP, and Crescendo attacks. Lower is safer.

How were Ministral 3 3B Base 2512 and Mistral NeMo Instruct 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