Meta Llama 3.1 405B Instruct vs Mistral Mistral Large 3 675B Instruct 2512 NVFP4

Detailed comparison for LLMs

MetaMistral

On Guardion's LLM vulnerability Benchmark, Mistral Mistral Large 3 675B Instruct 2512 NVFP4 is the more secure of the two: Llama 3.1 405B Instruct scores 36.0% and Mistral Large 3 675B Instruct 2512 NVFP4 scores 34.0% 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 NVFP4 is the overall winner in this comparison!

Attack Success Rate (lower is safer)

ASR for Meta Llama 3.1 405B Instruct vs Mistral Mistral Large 3 675B Instruct 2512 NVFP4. Green marks the safer model on each metric. Only the overall score is available for estimated models.

Overall (ASR)

Llama 3.1 405B Instruct
36.0%
Mistral Large 3 675B Instruct 2512 NVFP4
34.0%

TAP Attack Method (ASR)

Llama 3.1 405B Instruct
100.0%
Mistral Large 3 675B Instruct 2512 NVFP4
100.0%

Crescendo Attack Method (ASR)

Llama 3.1 405B Instruct
100.0%
Mistral Large 3 675B Instruct 2512 NVFP4
100.0%

Zero-Shot (ASR)

Llama 3.1 405B Instruct
100.0%
Mistral Large 3 675B Instruct 2512 NVFP4
100.0%

Key Highlights

  • Mistral Mistral Large 3 675B Instruct 2512 NVFP4 has a lower Overall (ASR).

Security Profile

Outward is better on every axis.

OverallTAPCrescendoZero-Shot
Llama 3.1 405B Instruct
Mistral Large 3 675B Instruct 2512 NVFP4
Full security profile
Meta Llama 3.1 405B Instruct
Full security profile
Mistral Mistral Large 3 675B Instruct 2512 NVFP4

Frequently asked questions

Is Meta Llama 3.1 405B Instruct or Mistral Mistral Large 3 675B Instruct 2512 NVFP4 more secure?

On Guardion's LLM vulnerability Benchmark, Mistral Mistral Large 3 675B Instruct 2512 NVFP4 is the more secure of the two: Llama 3.1 405B Instruct scores 36.0% and Mistral Large 3 675B Instruct 2512 NVFP4 scores 34.0% 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 Llama 3.1 405B Instruct vs Mistral Large 3 675B Instruct 2512 NVFP4?

Llama 3.1 405B Instruct has a 36.0% ASR and Mistral Large 3 675B Instruct 2512 NVFP4 has a 34.0% ASR — the share of adversarial prompts that succeed across zero-shot, TAP, and Crescendo attacks. Lower is safer.

How were Llama 3.1 405B Instruct and Mistral Large 3 675B Instruct 2512 NVFP4 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