Free AI attractiveness test · no sign-up
How Attractive Am I?
Take the attractiveness test: upload one selfie and get your attractiveness score out of 10 in seconds. AI maps 478 points on your face and measures the eight proportions people react to, from symmetry and the golden ratio to your jaw and eye tilt, then shows exactly what makes your face attractive and what holds the score back. Free, private, nothing uploaded.
Drop a photo, paste one, or choose a file
Straight-on, whole face visible, even light. JPG, PNG or WebP.
Runs in your browser. Your photo is never uploaded.
How it is measured
Eight proportions. One attractiveness score.
Faces people rate as attractive share a few measurable traits: they are symmetrical, their thirds are balanced, their width and height sit in a typical range, and the eyes tilt slightly up. The test measures eight of these on your photo, scores each against its reference band, weights them and adds them up into one number from 1 to 10. Every line is drawn on your face, so you can see where your score comes from.
- 8.0 and up
- Very attractive proportions: nearly every reading inside its band.
- 7.0 – 7.9
- Attractive proportions: most readings inside their bands.
- 6.0 – 6.9
- Above-average to average: a couple of readings sit outside.
- Under 6.0
- Several readings outside their bands. The breakdown names them.
Measure it yourself
How to get your most accurate score
The photo moves the score more than anything else. Take it like this:
- 1Face the camera straight on, eyes level, both ears equally visible.
- 2Hold the phone at arm's length or further. A close selfie widens the nose and shrinks the jaw.
- 3Use even light from the front, such as a window in front of you. No side shadows.
- 4Relax your face, close your mouth, push hair off your forehead. No filters or beauty mode.
- 5Retake and compare: the same face in a better photo often scores half a point higher.
Skip the ruler: the free tool above does it from one photo in about 30 seconds ↑
What's normal
What is a good attractiveness score?
Most straight-on photos land between 6 and 8. Here is how the scale reads:
- 8.5 – 9.6
- What it means: Exceptional proportions
- How common: Rare
- 7.5 – 8.4
- What it means: Very attractive proportions
- How common: Uncommon
- 6.5 – 7.4
- What it means: Attractive, above average
- How common: Common
- 5.5 – 6.4
- What it means: Average
- How common: Common
- Under 5.5
- What it means: Below average on proportions
- How common: Less common, often the photo
The score measures proportions. Skin, hair, style and expression are not in the number, and they can push how people see you up or down.
Sources
What this is based on.
The measurement and its reference ranges come from published research. Studies use different methods and populations, so compare your number with the range shown on this page rather than with other tools.
- 1.
Langlois JH, Kalakanis L, Rubenstein AJ, et al. (2000). Maxims or myths of beauty? A meta-analytic and theoretical review. Psychological Bulletin. doi:10.1037/0033-2909.126.3.390
Meta-analysis: people largely agree on who is attractive, across ages and cultures.
- 2.
Langlois JH, Roggman LA (1990). Attractive faces are only average. Psychological Science. doi:10.1111/j.1467-9280.1990.tb00079.x
Averaged composite faces were rated more attractive than most individual faces.
- 3.
Perrett DI, May KA, Yoshikawa S (1994). Facial shape and judgements of female attractiveness. Nature. doi:10.1038/368239a0
The most attractive faces were not simply average, so averageness is only part of the picture.
- 4.
Rhodes G (2006). The evolutionary psychology of facial beauty. Annual Review of Psychology. PubMed 16318594
Review of the main factors in facial attractiveness: averageness, symmetry and sex-typical features.
- 5.
Kartynnik Y, Ablavatski A, Grishchenko I, Grundmann M (2019). Real-time facial surface geometry from monocular video on mobile GPUs. arXiv. arXiv:1907.06724
The face-mesh model that places the 468 surface landmarks this tool measures from.
- 6.
Ablavatski A, Vakunov A, Grishchenko I, et al. (2020). Real-time pupil tracking from monocular video for digital puppetry. arXiv. arXiv:2006.11341
The iris model that adds 10 eye landmarks (478 in total), used for pupil-based reference lines.
Our own data: how much each reading moves when the same face is photographed again is published on the methodology page. How we choose sources.
Related tools
PSL Score Test
Your score on the 1–8 PSL scale, with your tier.
Pretty Scale Test
The same score as a 0–100% pretty scale.
Face Rating
The full 1–10 breakdown, reading by reading.
Face Symmetry Test
How symmetrical your face is, out of 100.
Canthal Tilt Calculator
Hunter-eye tilt in degrees.
Jawline Test
Jaw angle, width and chin.
FAQ
How attractive am I?+
Upload a straight-on selfie and the test gives you an attractiveness score out of 10, measured from eight facial proportions that studies link to attractiveness: symmetry, the golden ratio, facial thirds, face width to height, midface ratio, canthal tilt, jawline and eye spacing. You also see which of them make you attractive and which pull the score down.
Am I pretty?+
If your proportions sit inside the common bands, the test will show it: most readings in green and a score of 7 or more. Pretty is more than proportions, though. Skin, hair, makeup and expression change how people see you, so use the score as one honest data point, not a verdict.
Am I ugly?+
A low score almost never means ugly. It usually means the photo was taken too close, at an angle or in side light, or that one or two readings sit outside their band. Retake the photo straight on at arm's length and check the breakdown: it names the exact reading that pulled the number down.
Is this an AI attractiveness test?+
Yes. An AI face model finds 478 landmarks on your face, then the test measures the proportions between them. Unlike AI raters that guess a number, every reading here is drawn on your photo, so the score is explainable and the same photo always gets the same result.
How accurate is the attractiveness test?+
The measurements are consistent: the same photo always gets the same score, and photos taken the same way land close together (the methodology page publishes the repeatability data). What it measures is proportions, which are one part of attractiveness. A good photo matters: lens distance, head tilt and light move the score more than anything else.
What is a good attractiveness score?+
7 out of 10 and above means most of your proportions sit inside their reference bands, which is above average. 8 and above is uncommon. Most people score between 6 and 8.
Is my photo uploaded or saved?+
No. The test runs entirely in your browser. Your photo and your score never leave your device, there is no account and nothing is stored on a server.
Can I improve my attractiveness score?+
Partly. Bone readings like eye spacing and face width don't change, but jaw definition, facial symmetry, posture and the photo itself do. Retaking the photo straight on is the fastest win; the Symmi app tracks the readings that can change over weeks.
One reading here.
Nineteen in the app.
A controlled scan, every reading against its ideal band, bone vs trainable, a plan, and a 3D model on Face ID iPhones.