Mistral Mistral Large 2: LLM Security & Jailbreak Resistance
As of 2026-07-04, Mistral Mistral Large 2 has an attack success rate (ASR) of 42.0% on Guardion's LLM Vulnerability benchmark — ranking #63 of 93 models. It is weakly resistant — adversarial prompts succeed often without added guardrails.
Attack Success Rate (ASR) is the share of adversarial prompts that elicit harmful output across zero-shot, TAP, and Crescendo attacks (HarmBench framework). Lower is safer. "Est." models are calibrated from public safety evaluations pending a Guardion benchmark run.
How Mistral Large 2 compares
Frequently asked questions
How secure is Mistral Mistral Large 2 against jailbreaks?
Mistral Mistral Large 2 is weakly resistant — adversarial prompts succeed often without added guardrails. On Guardion's LLM Vulnerability benchmark it records a 42.0% attack success rate (58% robustness), ranking #63 of 93 models (estimated from public safety evaluations).
What is Mistral Large 2's attack success rate (ASR)?
Mistral Large 2's overall ASR is 42.0% — the share of adversarial prompts that elicit harmful output across zero-shot, TAP, and Crescendo attacks. Lower is safer.
Is Mistral Large 2 more secure than Mistral 8x22B?
Mistral 8x22B is more robust: 31.5% ASR vs Mistral Large 2's 42.0%. See the full head-to-head comparison for the per-attack breakdown.
How can I make Mistral Large 2 safer to deploy?
Even robust models are bypassed under sustained attack. An inline runtime guardrail that classifies prompts and responses — like Guardion's prompt-defense models — blocks jailbreaks and prompt injection before they reach Mistral Large 2.
Harden Mistral Large 2 in production
Guardion's runtime guardrails block jailbreaks and prompt injection before they reach any model — with sub-130ms policy decisions.
Request a demo