MiniMax MiniMax M1 40K vs Mistral Mistral Large 3 675B Instruct 2512

Detailed comparison for LLMs

MiniMaxMistral

On Guardion's LLM vulnerability Benchmark, Mistral Mistral Large 3 675B Instruct 2512 is the more secure of the two: MiniMax M1 40K scores 43.5% and Mistral Large 3 675B Instruct 2512 scores 33.0% 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 Large 3 675B Instruct 2512 is the overall winner in this comparison!

Attack Success Rate (lower is safer)

ASR for MiniMax MiniMax M1 40K vs Mistral Mistral Large 3 675B Instruct 2512. Green marks the safer model on each metric. Only the overall score is available for estimated models.

Overall (ASR)

MiniMax M1 40K
43.5%
Mistral Large 3 675B Instruct 2512
33.0%

TAP Attack Method (ASR)

MiniMax M1 40K
100.0%
Mistral Large 3 675B Instruct 2512
100.0%

Crescendo Attack Method (ASR)

MiniMax M1 40K
100.0%
Mistral Large 3 675B Instruct 2512
100.0%

Zero-Shot (ASR)

MiniMax M1 40K
100.0%
Mistral Large 3 675B Instruct 2512
100.0%

Key Highlights

  • Mistral Mistral Large 3 675B Instruct 2512 has a lower Overall (ASR).

Security Profile

Outward is better on every axis.

OverallTAPCrescendoZero-Shot
MiniMax M1 40K
Mistral Large 3 675B Instruct 2512
Full security profile
MiniMax MiniMax M1 40K
Full security profile
Mistral Mistral Large 3 675B Instruct 2512

Frequently asked questions

Is MiniMax MiniMax M1 40K or Mistral Mistral Large 3 675B Instruct 2512 more secure?

On Guardion's LLM vulnerability Benchmark, Mistral Mistral Large 3 675B Instruct 2512 is the more secure of the two: MiniMax M1 40K scores 43.5% and Mistral Large 3 675B Instruct 2512 scores 33.0% 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 M1 40K vs Mistral Large 3 675B Instruct 2512?

MiniMax M1 40K has a 43.5% ASR and Mistral Large 3 675B Instruct 2512 has a 33.0% ASR — the share of adversarial prompts that succeed across zero-shot, TAP, and Crescendo attacks. Lower is safer.

How were MiniMax M1 40K and Mistral Large 3 675B Instruct 2512 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