AI Attractiveness Test
Get your attractiveness score in about ten seconds. The analysis runs entirely in your browser — your photo is never uploaded, never stored, and never seen by us.
- 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.
How does an AI attractiveness test actually score a face?
It measures proportions, not beauty. A face mesh places 478 landmark points on the photo, and the score is a weighted combination of facial symmetry (40%) and three proportion ratios (20% each): face length to width, eye spacing to nose width, and nose length to mouth width. Nothing about the score is a judgement.
- Symmetry carries 40% of the score and is measured as the distance of six landmark pairs from the facial midline.
- The 0-100 composite is reported on a 1-10 scale because that is the unit the question is asked in.
- The photo is never uploaded — the model runs in the browser on the visitor's device.
- Research consistently finds averageness and symmetry predict rated attractiveness better than any single feature.
How attractive am I? What this test actually measures
The score is not an opinion. It is built from geometry your face already has: 478 landmark points are placed on your features, and from those we derive the measurements that facial-aesthetics research keeps returning to — bilateral symmetry, the ratios between thirds and fifths of the face, jaw definition, and eye spacing relative to face width.
Every one of those is a number you can check. The result page shows each measurement, what the reference range is, and where you sit inside it. A score with no breakdown is a magic trick; a score with the measurements attached is something you can argue with.
The attractiveness scale explained — what a 1-10 rating means
Scores cluster far more tightly than people expect. The overwhelming majority of faces land between 4 and 7, and the distance between a 5 and a 7 is usually two or three specific measurements, not a global difference in how someone looks.
That is the useful part of an attractiveness rating. Knowing you scored 6.1 tells you almost nothing. Knowing that your symmetry is in the top quartile while your lower-third proportion sits outside the reference range tells you exactly which two millimetres are doing the work.
Facial attractiveness test vs. a ChatGPT attractiveness test
Asking a chat model to rate your face gives you a plausible-sounding number with nothing underneath it. It cannot measure — it has no landmark detection, no reference distribution, and it will happily give the same photo a different score on a second run.
This test places actual landmarks and computes actual distances. Run the same photo twice and you get the same number, because it is arithmetic rather than a guess. That reproducibility is the whole difference between a measurement and a compliment.
Rate my face without uploading it — how the privacy works
The face mesh model is downloaded to your browser and runs on your device. Your selfie is processed in local memory and is never transmitted to a server, which means there is no upload to intercept, no storage bucket to breach, and no copy of your face for us to retain.
You can verify this yourself. Open your browser's network tab, run the test, and watch: the model file comes down, and nothing containing your image goes up.
What your attractiveness score does not tell you
Geometry is one input into how a face reads, and it is not the dominant one in real life. Expression, grooming, sleep, posture, lighting and the simple fact of liking someone all move the needle further than a two-millimetre ratio does.
Treat the number the way you would treat a body-composition reading: a measurement of one specific thing, useful precisely because it is narrow. It is not a verdict on you.
Tips for an accurate attractiveness score
- Shoot straight on. A few degrees of head rotation changes the measured distance on one side of every landmark pair.
- Hold the camera at arm's length, at eye level. Phone lenses are short and close, which enlarges whatever is nearest — usually the nose.
- Use even, front-facing light. Side light casts a shadow line that the mesh can read as an edge.
- Pull hair off the face and keep a neutral expression. A smile moves the mouth corners and the cheekbone landmarks together.
- No filters, no beauty mode. Phone cameras that smooth skin also subtly reshape features by default on many devices.
AI Attractiveness Test — frequently asked questions
Is this AI attractiveness test free?
Yes. The analysis, the score and the full measurement breakdown are free and require no account. Paid credits exist only for the optional simulation feature, which renders how a specific cosmetic procedure would change your face.
Do I need to sign up or upload my photo?
Neither. The face mesh runs in your browser, so the photo stays on your device. There is no account required to see your score.
How accurate is the attractiveness rating?
The measurements themselves are precise and reproducible — the same photo always returns the same numbers. How well those numbers predict real-world attraction is a much looser relationship, because expression, grooming and context matter more than geometry.
Why did my score change between photos?
Camera angle and lens distortion move the landmarks. A phone held close and low will widen the jaw and shorten the midface. For a comparable reading, use a straight-on photo at arm's length in even light.
What is a good attractiveness score?
Most faces score between 4 and 7, so anything in that band is unremarkable in the statistical sense. The breakdown is more informative than the total — it shows which specific measurements sit outside the reference range.
Does it work for men and women?
Yes. The reference ranges for several measurements differ by sex — jaw width and brow position most noticeably — and the analysis applies the appropriate set.
References
- 1.Rhodes, G. (2006). The evolutionary psychology of facial beauty. Annual Review of Psychology, 57, 199–226.
- 2.Grammer, K., & Thornhill, R. (1994). Human (Homo sapiens) facial attractiveness and sexual selection: the role of symmetry and averageness. Journal of Comparative Psychology, 108(3), 233–242.
- 3.Langlois, J. H., & Roggman, L. A. (1990). Attractive faces are only average. Psychological Science, 1(2), 115–121.
- 4.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.