Google Gemini 2.0 Flash vs OpenAI GPT-4o Mini
Detailed comparison for LLMs
On Guardion's LLM vulnerability Benchmark, OpenAI GPT-4o Mini is the more secure of the two: Gemini 2.0 Flash scores 33.6% and GPT-4o Mini scores 26.7% on attack success rate (ASR) (lower is better).
Head-to-Head Overview
GPT-4o Mini is the overall winner in this comparison!
Attack Success Rate (lower is safer)
ASR for Google Gemini 2.0 Flash vs OpenAI GPT-4o Mini. Green marks the safer model on each metric.
Overall (ASR)
TAP Attack Method (ASR)
Crescendo Attack Method (ASR)
Zero-Shot (ASR)
Key Highlights
- OpenAI GPT-4o Mini has a lower Overall (ASR).
- OpenAI GPT-4o Mini has a lower TAP Attack Method (ASR).
- Google Gemini 2.0 Flash has a lower Crescendo Attack Method (ASR).
- Google Gemini 2.0 Flash has a lower Zero-Shot (ASR).
Security Profile
Outward is better on every axis.
Frequently asked questions
Is Google Gemini 2.0 Flash or OpenAI GPT-4o Mini more secure?
On Guardion's LLM vulnerability Benchmark, OpenAI GPT-4o Mini is the more secure of the two: Gemini 2.0 Flash scores 33.6% and GPT-4o Mini scores 26.7% on attack success rate (ASR) (lower is better).
What is the attack success rate (ASR) of Gemini 2.0 Flash vs GPT-4o Mini?
Gemini 2.0 Flash has a 33.6% ASR and GPT-4o Mini has a 26.7% ASR — the share of adversarial prompts that succeed across zero-shot, TAP, and Crescendo attacks. Lower is safer.
How were Gemini 2.0 Flash and GPT-4o Mini 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.