DeepSeek DeepSeek-V3.2 Thinking vs Mistral Mistral Large 2
Detailed comparison for LLMs
DeepSeek DeepSeek-V3.2 Thinking and Mistral Mistral Large 2 are evenly matched at about 42.0% attack success rate (ASR) on Guardion's LLM vulnerability Benchmark. One or both scores are estimated from public safety evaluations pending a Guardion benchmark run.
Head-to-Head Overview
It's a close match between DeepSeek-V3.2 Thinking and Mistral Large 2!
Attack Success Rate (lower is safer)
ASR for DeepSeek DeepSeek-V3.2 Thinking vs Mistral Mistral Large 2. Green marks the safer model on each metric. Only the overall score is available for estimated models.
Overall (ASR)
TAP Attack Method (ASR)
Crescendo Attack Method (ASR)
Zero-Shot (ASR)
Key Highlights
No specific highlights generated for this comparison.
Security Profile
Outward is better on every axis.
Frequently asked questions
Is DeepSeek DeepSeek-V3.2 Thinking or Mistral Mistral Large 2 more secure?
DeepSeek DeepSeek-V3.2 Thinking and Mistral Mistral Large 2 are evenly matched at about 42.0% attack success rate (ASR) on Guardion's LLM vulnerability Benchmark. One or both scores are estimated from public safety evaluations pending a Guardion benchmark run.
What is the attack success rate (ASR) of DeepSeek-V3.2 Thinking vs Mistral Large 2?
DeepSeek-V3.2 Thinking has a 42.0% ASR and Mistral Large 2 has a 42.0% ASR — the share of adversarial prompts that succeed across zero-shot, TAP, and Crescendo attacks. Lower is safer.
How were DeepSeek-V3.2 Thinking and Mistral Large 2 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.