Am I Pretty?
A measured answer, not a verdict. The test scores four specific proportions of your face and shows you every one of them — so you can see what the number is made of instead of taking it on faith.
- No signup
- No upload
- Free
- ~10 seconds
Click to choose a photo, or drop one here
Straight-on, even lighting, at arm's length gives the most comparable reading.
No photo to hand? Try one of these and see what the tool returns.
Runs in your browser. Your photo is never uploaded.
Can a test tell you if you are pretty?
It can tell you your proportions, which is a different thing. This test measures symmetry and three facial ratios and reports them individually alongside a 1-10 composite. What it cannot do is settle the question you are asking, because rated attractiveness varies between raters, populations and decades.
- Every measurement behind the score is shown separately rather than folded into one number.
- Averageness and symmetry account for more of rated attractiveness than any individual feature.
- The photo runs through the model on your own device and is never transmitted.
How pretty am I? What a measured answer can and cannot say
A test can measure geometry. It can tell you that your face is symmetrical to within two per cent, that your midface proportion sits inside the reference range, that your jaw is defined. Those are facts about distances.
It cannot tell you whether people find you attractive, because that is decided by expression, warmth, grooming, health, style and context — none of which live in a landmark. Anyone selling you a number as a verdict on your face is selling you something false.
The pretty scale explained — what a 1-10 score really means
Scores bunch up hard in the middle. The overwhelming majority of faces land between 4 and 7, and the gap between a 5 and a 7 is typically two or three specific measurements rather than a global difference in how someone looks.
This is the part worth internalising: a low score is almost never a face that is wrong everywhere. It is a face with one or two measurements outside the reference band and the rest entirely ordinary.
Am I pretty or ugly? Why that question has no measurable answer
There is no threshold in the data. Nothing in the geometry marks where one category stops and another starts — the distribution is a smooth hill with no valley in it, which is exactly what you would expect from a trait with no natural boundary.
If you came to this page with that question, the most accurate answer available is that the categories are not real. What is real is a set of measurements, and they cluster far closer to average than the question assumes.
How pretty am I, scientifically? What the research supports
The findings that replicate are unglamorous. Symmetry has a small positive relationship with rated attractiveness. Averageness — a face close to the population mean — has a larger one. Clear skin has a larger one still, and it is the most changeable of the three.
What does not replicate well is the golden ratio, despite how often it is quoted. That is why this test reports symmetry and proportion separately rather than folding everything into one number and calling it science.
Your photo never leaves your device
The face mesh model downloads to your browser and the analysis runs on your device. Your photo is held in local memory, never transmitted, never stored. There is no upload for us to keep and no image for anyone to see.
For a question this personal, that matters more than usual — and you can verify it yourself in your browser's network panel.
Tips for a fair reading
- Straight on, arm's length, eye level. Selfies taken from below widen the jaw and shorten the midface.
- Even light, no filter, hair off the face.
- Run it more than once with different photos. If the number moves several points, the photos are doing the work, not your face.
Am I Pretty? — frequently asked questions
Is this beauty test free?
Yes, with no account. The score and the full measurement breakdown are free. Paid credits apply only to the optional simulation feature.
How accurate is an am I pretty test?
The measurements are precise and reproducible — the same photo always returns the same numbers. How well those numbers predict whether people find you attractive is a much weaker relationship, because expression and grooming matter more than geometry.
What is an average score on the pretty scale?
Most faces score between 4 and 7 out of 10. That band is genuinely unremarkable in the statistical sense, which is worth remembering if you land in it.
Why did I get a different score in a different photo?
Camera angle and lens distortion move the landmarks. A phone held low and close widens the jaw and shortens the midface. Use a straight-on photo at arm's length in even light for a comparable reading.
Does it work for men?
Yes. Several reference ranges differ by sex — jaw width and brow position most noticeably — and the analysis applies the appropriate set.
Should I take this seriously?
Take it as seriously as a tape measure. It reports distances accurately and nothing else. It is not a judgement, and a low number on one proportion is not a statement about you.
References
- 1.Langlois, J. H., & Roggman, L. A. (1990). Attractive faces are only average. Psychological Science, 1(2), 115–121.
- 2.Rhodes, G. (2006). The evolutionary psychology of facial beauty. Annual Review of Psychology, 57, 199–226.
- 3.Fink, B., Grammer, K., & Matts, P. J. (2006). Visible skin color distribution plays a role in the perception of age, attractiveness, and health in female faces. Evolution and Human Behavior, 27(6), 433–442.