Detailed comparison for LLMs
On Guardion's LLM vulnerability Benchmark, Mistral Ministral 3 3B Reasoning 2512 is the more secure of the two: Ministral 3 3B Reasoning 2512 scores 46.0% and Deepseek V3 scores 47.2% on attack success rate (ASR) (lower is better). One or both scores are estimated from public safety evaluations pending a Guardion benchmark run.
Ministral 3 3B Reasoning 2512 is the overall winner in this comparison!
ASR for Mistral Ministral 3 3B Reasoning 2512 vs Deepseek Deepseek V3. Green marks the safer model on each metric. Only the overall score is available for estimated models.
Outward is better on every axis.
On Guardion's LLM vulnerability Benchmark, Mistral Ministral 3 3B Reasoning 2512 is the more secure of the two: Ministral 3 3B Reasoning 2512 scores 46.0% and Deepseek V3 scores 47.2% on attack success rate (ASR) (lower is better). One or both scores are estimated from public safety evaluations pending a Guardion benchmark run.
Ministral 3 3B Reasoning 2512 has a 46.0% ASR and Deepseek V3 has a 47.2% ASR — the share of adversarial prompts that succeed across zero-shot, TAP, and Crescendo attacks. Lower is safer.
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.