Looksmaxxing Test
17 metrics · AI glow-up plan
Tests
Smile Analyzer
Genuine vs fake smile · instant AI read
Compare Photos
Which photo gets more matches?
Golden Ratio Test
Facial proportions vs ideal
Face Metrics
measured in the looksmaxxing test
Explore
Measurements Explained
The 17-metric video series — honest answers
Guides
Dating & LinkedIn photo tips
Blog
Looksmaxxing articles
Celebrity Scores
How famous faces rank
Free Widget Embed
Add face analysis to your site
About
Our mission & team
Facial Analysis Reference Ranges & Methodology
Anthropometric reference ranges and methodology behind RealSmile's 17-metric facial analysis. Sources: Farkas, Holland, Ricketts, Carre & McCormick, Grammer & Thornhill, and Rhodes.
Cite this page
RealSmile. (2026). Facial Analysis Reference Ranges & Methodology. Retrieved August 21, 2026, from https://realsmile.online/research
Free to use with attribution. License: CC-BY-4.0.
17
Metrics scored
Geometric measurements derived from the 68-point iBUG 300-W landmark scheme used by face-api.js
4–8°
Average canthal tilt
Published normative range for adult positive canthal tilt (Farkas, 1994)
120–135°
Ideal gonial angle
Cephalometric ideal range used in orthodontics and maxillofacial surgery (Proffit, 2018)
1.75–1.95
Typical FWHR range
Most measured adults fall in this facial width-to-height ratio range in published cephalometric data (Carre & McCormick, 2008)
23%
Lighting symmetry shift
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
Lighting changes shift attractiveness ratings more than most cosmetic interventions (St Andrews, 2004)
30+
Cultures studied
Symmetry preferences confirmed cross-culturally (Rhodes, 2006)
0.5°/decade
Canthal tilt aging
Average rate at which positive canthal tilt decreases after age 30 (Farkas, 1994)
φ ≈ 1.618
Golden ratio
Phi-based proportions referenced in Ricketts (1982); however, averageness predicts attractiveness more reliably (Langlois & Roggman, 1990)
Key Research Findings (Peer-Reviewed Literature)
Summary findings from peer-reviewed facial-aesthetics literature, used to anchor the reference ranges and metric calibration in RealSmile’s client-side face-api.js (68-point iBUG 300-W) analysis.
- 1.Facial symmetry preferences are present from infancy and have been confirmed across 30+ cultures (Rhodes, 2006).
- 2.Average positive canthal tilt is 4–8 degrees in adults, varying by ethnicity and age, and decreases approximately 0.5° per decade after age 30 (Farkas, 1994).
- 3.Facial width-to-height ratio (FWHR) is moderately correlated with perceived dominance and weakly correlated with overall perceived attractiveness; effect sizes are smaller than originally reported (Carre & McCormick, 2008; Geniole et al., 2015).
- 4.Phi-based golden-ratio templates do not reliably predict perceived attractiveness; facial averageness is a stronger predictor (Holland, 2008; Langlois & Roggman, 1990).
- 5.The orthodontic ideal gonial angle range is approximately 120–135°; forward head posture alone can increase the apparent angle by 3–8° (Proffit, 2018; Arnett & Gunson, 2004).
- 6.Shorter midface ratios are linked to neoteny, which cross-cultural research associates with higher attractiveness ratings (Perrett et al., 1998).
- 7.Equal facial thirds (each section ~33%) have been a standard of facial aesthetics since da Vinci's Vitruvian proportions and remain in use as a diagnostic tool in modern orthodontic analysis (Farkas & Munro, 1987; Naini, 2011).
- 8.Asymmetric lighting can increase perceived asymmetry on the same face by up to 23% (Zaidel & Cohen, 2005), and lighting changes can shift overall attractiveness ratings by approximately 1.5 standard deviations (St Andrews, 2004) — larger than most cosmetic interventions.
- 9.Humans form attractiveness and trustworthiness judgments from faces in approximately 33 milliseconds (Todorov & Porter, 2014).
- 10.RealSmile's scoring engine maps individual measured values onto these published reference ranges; per-user analyses are not retained or aggregated into private datasets.
Metric-by-Metric Breakdown
Facial Symmetry
Test yours free →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
55–95
Distribution
Most measured faces fall in the 65–80 range in published anthropometric studies
Key Finding
Self-perceived asymmetry consistently exceeds measured asymmetry: most people who describe themselves as "very asymmetric" measure within a few percentage points of perfect bilateral symmetry. Symmetry scores above 85 are uncommon in the published literature.
Research
Grammer, K. & Thornhill, R. (1994). "Human (Homo sapiens) facial attractiveness and sexual selection." Journal of Comparative Psychology, 108(3), 233–242. Rhodes, G. (2006). "The evolutionary psychology of facial beauty." Annual Review of Psychology, 57, 199–226. Found symmetry preferences present from infancy across 30+ cultures.
Canthal Tilt
Test yours free →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
5.2°
Range
2–10°
Distribution
Most measured adults fall in the 3–7° positive tilt range (Farkas, 1994)
Key Finding
Negative canthal tilt (outer corner lower) is the most commonly searched "weak" metric in the looksmaxxing community. Among published anthropometric ranges, positive canthal tilt shows one of the strongest single-metric associations with overall perceived attractiveness.
Research
Farkas, L.G. (1994). "Anthropometry of the Head and Face." Raven Press, New York. Established normative canthal tilt data. Average positive canthal tilt is 4–8 degrees, varying by ethnicity and age. Tilt decreases approximately 0.5° per decade after age 30.
Facial Width-to-Height Ratio (FWHR)
Test yours free →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
1.6–2.2
Distribution
Most measured adults fall in the 1.75–1.95 range in published cephalometric data
Key Finding
FWHR above 2.0 is associated with higher perceived dominance and assertiveness in published facial-aesthetics research. The relationship between FWHR and actual behavior has been debated in recent meta-analyses, with effect sizes smaller than originally reported.
Research
Carre, J.M. & McCormick, C.M. (2008). "In your face: facial metrics predict aggressive behaviour in the laboratory and in varsity and professional hockey players." Proceedings of the Royal Society B, 275(1651), 2651–2656. Geniole, S.N. et al. (2015). "Facing aggression: cues differ for female vs. male faces." PLOS ONE, 10(8). Effect sizes are smaller than originally reported.
Golden Ratio Adherence
Test yours free →Golden ratio adherence measures how closely facial proportions approximate the mathematical ratio phi (φ = 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
40–92
Distribution
Most measured faces fall in the 58–78 range when scored against phi-based templates
Key Finding
Faces scoring above 85 on golden ratio adherence are rare in published anthropometric literature. High golden ratio scores do not reliably correlate with high overall attractiveness — facial harmony and averageness appear to be stronger predictors (Holland, 2008; Langlois & Roggman, 1990).
Research
Ricketts, R.M. (1982). "The biologic significance of the divine proportion and Fibonacci series." American Journal of Orthodontics, 81(5), 351–370. Holland, E. (2008). "Marquardt's Phi Mask: pitfalls of relying on fashion models and the golden ratio to describe a beautiful face." Aesthetic Plastic Surgery, 32(2), 200–208. Langlois, J.H. & Roggman, L.A. (1990). "Attractive faces are only average." Psychological Science, 1(2), 115–121.
Jawline / Gonial Angle
Test yours free →The gonial angle is the angle formed at the gonion — 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
135°
Range
118–152°
Distribution
Most measured adults fall in the 128–142° range in cephalometric standards (Proffit, 2018)
Key Finding
Jawline angle is among the most improvable visible metrics. Body fat reduction, posture correction, and masseter training can shift the apparent gonial angle by 3–12 degrees. Forward head posture alone accounts for 3–8 degrees of increased apparent angle (Proffit, 2018; Arnett & Gunson, 2004).
Research
The ideal gonial angle range of 120–135° is based on cephalometric analysis standards used in orthodontics and maxillofacial surgery. Proffit, W.R. et al. (2018). "Contemporary Orthodontics," 6th Edition, Elsevier. Arnett, G.W. & Gunson, M.J. (2004). "Facial planning for orthodontists and oral surgeons." American Journal of Orthodontics and Dentofacial Orthopedics, 126(3), 290–295.
Midface Ratio
Test yours free →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
0.38–0.52
Distribution
Most measured adults fall in the 0.41–0.48 range in published anthropometric data
Key Finding
Midface ratio is the least modifiable visible metric through non-surgical means. It is primarily determined by skeletal structure. Hairstyle changes that alter perceived forehead height can shift the apparent midface ratio modestly. Shorter midface ratios are linked to neoteny and higher cross-cultural attractiveness ratings (Perrett et al., 1998).
Research
Shorter midface ratios are associated with neoteny (youthful appearance), which cross-cultural research links to higher attractiveness ratings. Perrett, D.I. et al. (1998). "Effects of sexual dimorphism on facial attractiveness." Nature, 394, 884–887. Enlow, D.H. & Hans, M.G. (1996). "Essentials of Facial Growth." W.B. Saunders.
Facial Thirds Balance
Test yours free →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
45–95
Distribution
Elongated lower third (>36% of face height) is the most common imbalance reported in cephalometric literature
Key Finding
The most common imbalance is an elongated lower third, often linked to mouth breathing during development or dental malocclusion. Strategic facial hair can visually rebalance facial thirds in men. Faces with all three sections within 2% of equal (31.3–35.3% each) are uncommon in published anthropometric data (Farkas & Munro, 1987; Naini, 2011).
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. Farkas, L.G. & Munro, I.R. (1987). "Anthropometric Facial Proportions in Medicine." Charles C. Thomas Publisher. Naini, F.B. (2011). "Facial Aesthetics: Concepts and Clinical Diagnosis." Wiley-Blackwell.
How Lighting Affects All Metrics
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 3–8°, reduces symmetry scores by 5–12%, and can create false negative canthal tilt readings.
Optimal Lighting
Soft, front-facing light at 15–30° elevation produces the most accurate measurements. Window light or golden hour sunlight is ideal for both accuracy and flattery.
Methodology
Face Detection and Landmark Extraction
All data is derived from analyses run through RealSmile's tools. Face detection uses face-api.js (@vladmandic/face-api) built on TensorFlow.js. The model detects 68 facial landmarks per face following the iBUG 300-W annotation scheme, which identifies key points across the jawline (landmarks 0–16), eyebrows (17–26), nose (27–35), eyes (36–47), and mouth (48–67).
Metric Calculation Methods
Each metric is calculated from specific landmark positions using geometric formulas:
- --Facial Symmetry: Euclidean distance comparisons between corresponding left/right landmarks (e.g., landmark 36 vs 45 for outer eye corners), normalized against face width and expressed as a percentage.
- --Canthal Tilt: Angle between inner canthus (landmarks 39, 42) and outer canthus (landmarks 36, 45) relative to the horizontal axis, measured in degrees using atan2.
- --FWHR: Bizygomatic width (horizontal distance between landmarks 1 and 15) divided by upper facial height (vertical distance from landmark 51 to midpoint of landmarks 21 and 22).
- --Golden Ratio: Multiple phi-ratio (1.618) comparisons across facial proportions: face height/width, mouth-to-nose/nose-to-eye, and interpupillary distance relative to face width.
- --Gonial Angle: Estimated from the jawline landmark trajectory (landmarks 4–8 and 8–12), calculating the angle at the jaw's inflection point.
- --Midface Ratio: Vertical distance from eye level (midpoint of landmarks 37/38 and 43/44) to upper lip (landmark 51) divided by total face height (landmark 8 to midpoint of landmarks 19/24).
- --Facial Thirds: Face divided into upper (hairline estimate to brow ridge), middle (brow to nose base, landmarks 19/24 to 33), and lower (nose base to chin, landmarks 33 to 8), expressed as percentage balance.
Data Collection and Privacy
All analyses are performed client-side in users' browsers. No photos are transmitted to or stored on any server. RealSmile does not store individual results or identifiable data. Aggregated statistics are derived from anonymized score distributions (metric scores only, with no demographic or identifying information) logged with user consent via analytics events.
Reference Range Source
All reference ranges shown on this page are sourced from peer-reviewed anthropometric and facial-aesthetics literature (cited per metric above). RealSmile's scoring engine maps each user's measured value onto these published ranges. Individual user analyses are not stored, retained, or used to construct private datasets.
Limitations and Disclaimer
Research citations reference peer-reviewed published studies. RealSmile's tool methodology is informed by but not identical to clinical cephalometric analysis. Landmark-based analysis from 2D photos introduces inherent limitations compared to 3D imaging: pose angle, lens distortion, and lighting affect measurements. Scores should be interpreted as relative measurements for self-improvement tracking, not clinical diagnostic data. Correlation coefficients reported are Pearson r values calculated within this dataset and may differ from clinical study populations.
Reference This Page
This page summarizes anthropometric reference ranges from peer-reviewed literature; it is not primary research. If you cite a specific finding, please cite the underlying study (listed alongside each metric above) directly. If you wish to link to this page as a methodology summary, the format below is appropriate:
Methodology Reference
RealSmile (2026). Facial Analysis Reference Ranges & Methodology. https://realsmile.online/research
All scientific findings on this page are attributable to the cited peer-reviewed studies, not to RealSmile. Last updated: March 2026.
Companion bibliography
The peer-reviewed studies behind these metrics
12 published papers from Penton-Voak, Rhodes, Perrett, Little, and others — the foundational research that informs every metric on this page.
Read the bibliography →Measure Your Own Metrics
Free, instant, private. All analysis runs in your browser — no photos stored.