Detailed comparison for LLMs
On Guardion's LLM vulnerability Benchmark, Google Gemma 3n E4B Instructed is the more secure of the two: Ministral 3 3B Instruct 2512 scores 50.0% and Gemma 3n E4B Instructed scores 49.0% on attack success rate (ASR) (lower is better). One or both scores are estimated from public safety evaluations pending a Guardion benchmark run.
Gemma 3n E4B Instructed is the overall winner in this comparison!
ASR for Mistral Ministral 3 3B Instruct 2512 vs Google Gemma 3n E4B Instructed. 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, Google Gemma 3n E4B Instructed is the more secure of the two: Ministral 3 3B Instruct 2512 scores 50.0% and Gemma 3n E4B Instructed scores 49.0% 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 Instruct 2512 has a 50.0% ASR and Gemma 3n E4B Instructed has a 49.0% 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.