Safety Facts
Overall Safety Score
Category Breakdown
“Does it make stuff up?”
Good truthfulness for a fast model.
Gemini 2.0 Flash shows solid truthfulness while maintaining high speed. It handles factual questions well and generally acknowledges uncertainty appropriately.
Benchmarks Used
“Does it treat people differently?”
Improved fairness over previous Flash model.
“Can you trick it into saying dangerous things?”
Strong safety at the fast tier.
“Does it try to manipulate you?”
Generally fair information presentation.
Gemini 2.0 Flash presents information fairly, though occasionally with less nuance than the Pro models.
Benchmarks Used
“Does it leak personal info?”
Reasonable privacy protections.
Gemini 2.0 Flash shows moderate privacy behavior, generally declining to share private information.
Benchmarks Used
“Does it just tell you what you want to hear?”
Can be somewhat agreeable.
Gemini 2.0 Flash shows moderate sycophancy, sometimes agreeing with users rather than correcting them.
Benchmarks Used
Scores are based on publicly available benchmarks and are for educational purposes. They do not constitute endorsements or guarantees of safety. View full methodology
Ranked #14 of 22 models
Evaluated February 21, 2026
Version History
Found a safety issue with Gemini 2.0 Flash?
Help improve our scores by reporting your findings.
Report an Issue