Google Gemini 2.0 Flash Thinking vs Google Gemini 2.0 Flash Lite
Detailed comparison for LLMs
On Guardion's LLM vulnerability Benchmark, Google Gemini 2.0 Flash Thinking is the more secure of the two: Gemini 2.0 Flash Thinking scores 21.5% and Gemini 2.0 Flash Lite scores 31.3% on attack success rate (ASR) (lower is better). One or both scores are estimated from public safety evaluations pending a Guardion benchmark run.
Head-to-Head Overview
Gemini 2.0 Flash Thinking is the overall winner in this comparison!
Attack Success Rate (lower is safer)
ASR for Google Gemini 2.0 Flash Thinking vs Google Gemini 2.0 Flash Lite. 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
- Google Gemini 2.0 Flash Thinking has a lower Overall (ASR).
- Google Gemini 2.0 Flash Lite has a lower TAP Attack Method (ASR).
- Google Gemini 2.0 Flash Lite has a lower Crescendo Attack Method (ASR).
- Google Gemini 2.0 Flash Lite has a lower Zero-Shot (ASR).
Security Profile
Outward is better on every axis.
Frequently asked questions
Is Google Gemini 2.0 Flash Thinking or Google Gemini 2.0 Flash Lite more secure?
On Guardion's LLM vulnerability Benchmark, Google Gemini 2.0 Flash Thinking is the more secure of the two: Gemini 2.0 Flash Thinking scores 21.5% and Gemini 2.0 Flash Lite scores 31.3% on attack success rate (ASR) (lower is better). One or both scores are estimated from public safety evaluations pending a Guardion benchmark run.
What is the attack success rate (ASR) of Gemini 2.0 Flash Thinking vs Gemini 2.0 Flash Lite?
Gemini 2.0 Flash Thinking has a 21.5% ASR and Gemini 2.0 Flash Lite has a 31.3% ASR — the share of adversarial prompts that succeed across zero-shot, TAP, and Crescendo attacks. Lower is safer.
How were Gemini 2.0 Flash Thinking and Gemini 2.0 Flash Lite 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.