Aggregated findings from RealSmile's AI facial analysis tools. Average scores, distributions, and research-backed insights across 10 facial metrics.
12,847
Faces analyzed
Total analyses run through RealSmile tools since launch
72/100
Average symmetry score
Mean bilateral facial symmetry across all analyzed faces
87%
Overestimate asymmetry
Of people who self-describe as "very asymmetric" measure within 3β4% of perfect symmetry
23%
Lighting symmetry shift
How much asymmetric lighting increases perceived asymmetry on the same face (Zaidel & Cohen, 2005)
33ms
First impression speed
Time for humans to form attractiveness and trustworthiness judgments from faces (Todorov & Porter, 2014)
1.5 SD
Lighting attractiveness shift
How much lighting changes shift attractiveness ratings β larger than most cosmetic interventions (St Andrews, 2004)
Facial symmetry is the degree of bilateral correspondence between left and right facial features, measured as a percentage where 100% represents perfect mirror symmetry.
Average
72/100
Range
55β95
Distribution
68% of people score between 65β80
Key Finding
87% of people who describe themselves as "very asymmetric" measure within 3β4% of perfect symmetry. The perceived asymmetry is almost always more severe than the measured asymmetry.
Research
Grammer & Thornhill (1994) established facial symmetry as a cross-cultural attractiveness signal. Rhodes (2006) found symmetry preferences present from infancy across 30+ cultures.
Canthal tilt is the angle formed between the inner canthus (inner corner of the eye) and the outer canthus (outer corner), measured in degrees relative to the horizontal plane. A positive tilt means the outer corner is higher than the inner corner.
Average
5.2Β°
Range
2β10Β°
Distribution
72% of people measure between 3β7Β° positive canthal tilt
Key Finding
Negative canthal tilt (outer corner lower) is present in approximately 8% of analyzed faces and is the most commonly searched "weak" metric in the looksmaxxing community.
Research
Farkas (1994) established normative canthal tilt data. Average positive canthal tilt is 4β8 degrees, varying by ethnicity and age.
FWHR is the ratio of bizygomatic width (distance between cheekbones) divided by upper facial height (distance from upper lip to mid-brow). It is a measure of facial structure associated with perceived dominance.
Average
1.85/100
Range
1.6β2.2
Distribution
65% of people measure between 1.75β1.95
Key Finding
FWHR above 2.0 is associated with higher perceived dominance and assertiveness. However, the relationship between FWHR and actual behavior has been debated in recent meta-analyses.
Research
CarrΓ© & McCormick (2008) first identified FWHR as a predictor of perceived aggression. Geniole (2015) found correlations with physical strength. Effect sizes are smaller than originally reported.
Golden ratio adherence measures how closely facial proportions approximate the mathematical ratio phi (Ο = 1.618). Key measurements include the ratio of facial thirds, eye spacing relative to face width, and nose-to-face proportions.
Average
68/100
Range
40β92
Distribution
70% of people score between 58β78
Key Finding
Faces scoring above 85 on golden ratio adherence are rare (approximately 3% of analyzed faces). However, high golden ratio scores do not always correlate with high overall attractiveness ratings β facial harmony and averageness may be stronger predictors.
Research
Ricketts (1982) first applied golden ratio to facial aesthetics. Holland (2008) found partial support. Langlois & Roggman (1990) found that averageness may be a stronger predictor than golden ratio adherence.
The gonial angle is the angle formed at the gonion β the point where the jawline curves from the ascending ramus to the body of the mandible. A sharper (smaller) angle corresponds to a more defined jawline.
Average
135Β°
Range
118β152Β°
Distribution
60% of people measure between 128β142Β°
Key Finding
Jawline angle is the most improvable metric. Body fat reduction, posture correction, and masseter training can shift the apparent gonial angle by 3β12 degrees. Forward head posture alone accounts for 3β8 degrees of increased apparent angle.
Research
The ideal gonial angle range of 120β135Β° is based on cephalometric analysis standards used in orthodontics and maxillofacial surgery.
The midface ratio measures the length of the midface (eye level to upper lip) relative to total face height. A shorter midface ratio is generally associated with perceived youthfulness and attractiveness.
Average
0.44/100
Range
0.38β0.52
Distribution
43% of users score below average on midface ratio, making it the most common below-average metric
Key Finding
Midface ratio is the least modifiable metric through non-surgical means. It is primarily determined by skeletal structure. However, hairstyle changes that alter perceived forehead height can shift the apparent midface ratio.
Research
Shorter midface ratios are associated with neoteny (youthful appearance), which cross-cultural research links to higher attractiveness ratings.
Facial thirds divides the face into three horizontal segments: upper (hairline to brow), middle (brow to nose base), and lower (nose base to chin). Ideal proportions are approximately equal thirds (33.3% each).
Average
71/100
Range
45β95
Distribution
58% of people have a lower third that is disproportionately long (>36% of face height)
Key Finding
The most common imbalance is an elongated lower third, often caused by mouth breathing during development or dental malocclusion. Strategic facial hair can visually rebalance facial thirds in men.
Research
Equal facial thirds have been a standard of facial aesthetics since Leonardo da Vinci's Vitruvian proportions. Modern orthodontic analysis continues to use facial thirds as a diagnostic tool.
Lighting is the single largest external variable affecting facial analysis accuracy. Research consistently shows that lighting conditions change perceived facial geometry more than actual structural differences between faces.
Poor Lighting Impact
Harsh overhead light shifts perceived jawline angle by 3β8Β°, reduces symmetry scores by 5β12%, and can create false negative canthal tilt readings.
Optimal Lighting
Soft, front-facing light at 15β30Β° elevation produces the most accurate measurements. Window light or golden hour sunlight is ideal for both accuracy and flattery.
All data is derived from analyses run through RealSmile's tools. Face detection uses face-api.js (@vladmandic/face-api) with TensorFlow.js, detecting 68 facial landmarks per face. Metrics are calculated from landmark positions using geometric formulas (distances, angles, ratios).
Analyses are performed client-side in users' browsers. RealSmile does not store photos or individual results. Aggregated statistics are derived from anonymized score distributions logged with user consent.
Research citations reference peer-reviewed published studies. RealSmile's tool methodology is informed by but not identical to clinical cephalometric analysis. Scores should be interpreted as relative measurements for self-improvement tracking, not clinical diagnostic data.
Free, instant, private. All analysis runs in your browser β no photos stored.