MiniMax MiniMax M2 vs Mistral Mistral NeMo Instruct

Detailed comparison for LLMs

MiniMaxMistral

On Guardion's LLM vulnerability Benchmark, MiniMax MiniMax M2 is the more secure of the two: MiniMax M2 scores 40.0% 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

MiniMax M2 is the overall winner in this comparison!

Attack Success Rate (lower is safer)

ASR for MiniMax MiniMax M2 vs Mistral Mistral NeMo Instruct. Green marks the safer model on each metric. Only the overall score is available for estimated models.

Overall (ASR)

MiniMax M2
40.0%
Mistral NeMo Instruct
50.0%

TAP Attack Method (ASR)

MiniMax M2
100.0%
Mistral NeMo Instruct
100.0%

Crescendo Attack Method (ASR)

MiniMax M2
100.0%
Mistral NeMo Instruct
100.0%

Zero-Shot (ASR)

MiniMax M2
100.0%
Mistral NeMo Instruct
100.0%

Key Highlights

  • MiniMax MiniMax M2 has a lower Overall (ASR).

Security Profile

Outward is better on every axis.

OverallTAPCrescendoZero-Shot
MiniMax M2
Mistral NeMo Instruct
Full security profile
MiniMax MiniMax M2
Full security profile
Mistral Mistral NeMo Instruct

Frequently asked questions

Is MiniMax MiniMax M2 or Mistral Mistral NeMo Instruct more secure?

On Guardion's LLM vulnerability Benchmark, MiniMax MiniMax M2 is the more secure of the two: MiniMax M2 scores 40.0% 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 MiniMax M2 vs Mistral NeMo Instruct?

MiniMax M2 has a 40.0% 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 MiniMax M2 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