Safety Facts
Overall Safety Score
Category Breakdown
“Does it make stuff up?”
Good reasoning-based truthfulness at smaller scale.
o1-mini maintains the reasoning approach of o1 in a more efficient package. While slightly less capable, it still shows strong truthfulness through deliberate thinking.
Benchmarks Used
“Does it treat people differently?”
Maintains fairness at efficient scale.
“Can you trick it into saying dangerous things?”
Strong safety maintained at smaller scale.
“Does it try to manipulate you?”
Generally balanced responses.
o1-mini presents information fairly, using reasoning to avoid manipulative framing.
Benchmarks Used
“Does it leak personal info?”
Good privacy behavior.
o1-mini shows reasonable privacy behavior, generally refusing to share private information.
Benchmarks Used
“Does it just tell you what you want to hear?”
Moderate sycophancy resistance.
o1-mini shows reasonable resistance to sycophantic behavior, though slightly more agreeable than the full o1.
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 #12 of 22 models
Evaluated February 21, 2026
Found a safety issue with o1-mini?
Help improve our scores by reporting your findings.
Report an Issue