Measure your facial symmetry with AI precision. 478 landmarks, 5 feature scores, processed in your browser.
Upload a photo
Drag and drop or click to browse
JPG, PNG up to 10MB
Your photo never leaves your device
Facial symmetry measures how closely the left and right sides of your face mirror each other when reflected across a vertical midline. No human face is perfectly symmetric — even faces widely considered the most attractive show measurable bilateral differences. Most people score between 70 and 85 on a 100-point scale, and asymmetry below 3% is generally imperceptible to observers (the Farkas standard).
Symmetry is one factor in perceived attractiveness, but not the only one — and beyond a certain threshold, more symmetry doesn't continue to add appeal. A balanced 80-range score is typical of faces rated as attractive in clinical studies.
The overall symmetry score is a weighted average of five feature scores (eyes, eyebrows, nose, mouth, jaw), each scaled 0–100. Here is what each band means in practice.
| Score | Label | Population | What it means | Visibility |
|---|---|---|---|---|
| 90–100 | Excellent | Top 5–10% | The two sides of the face are nearly indistinguishable when mirrored. Differences are detectable only by precise measurement. | Not perceptible to observers in normal viewing. |
| 80–89 | Good | Roughly the next 20–25% | Subtle differences exist, typically in one feature pair (often jaw or mouth). The face reads as balanced overall. | Rarely noticed even in photos. |
| 70–79 | Average | Largest group — most people score here | Mild asymmetry, usually a mix of soft tissue and habitual patterns. Often more visible in unflipped photos than in the mirror. | Occasionally noticeable in photos; rarely in conversation. |
| Below 70 | Below Average | Bottom 15–20% | Distinct asymmetry in one or more features. Often muscular (one-sided chewing, habitual expression patterns) and frequently improvable with targeted intervention. | Generally visible in photos and sometimes in person. |
The tool computes a separate symmetry score for each of five feature groups by comparing bilateral landmark pairs against a stable facial midline. A low score in one feature can pull the overall down even when other features are well-balanced.
What it measures: Compares the positions of the inner and outer corners of each eye, plus the upper and lower lid contour, against the facial midline. Detects differences in eye height, opening width, and tilt.
Common causes of asymmetry: Orbicularis oculi muscle imbalance, ptosis (drooping lid) on one side, sleeping position causing fluid retention, prior lid surgery, neurological causes (rare).
What it measures: Compares the positions of the brow head, peak, and tail on each side. Detects differences in arch height, brow length, and resting position.
Common causes of asymmetry: Frontalis muscle dominance on one side, habitual brow-raising patterns, asymmetric eyebrow grooming, congenital differences in brow placement.
What it measures: Compares bridge points, nostril edges, and tip position against the facial midline. Detects bridge deviation, nostril size differences, and tip asymmetry.
Common causes of asymmetry: Deviated septum (often genetic), prior nasal trauma, post-rhinoplasty asymmetry, habitual one-sided nose-touching, congenital nostril shape differences.
What it measures: Compares the lip corners (commissures), the cupid's bow peaks, and the lower lip contour. Detects differences in resting lip-corner height and lip volume balance.
Common causes of asymmetry: Zygomaticus muscle dominance (the 'crooked smile'), habitual one-sided expression, dental issues affecting lip support, Bell's palsy or similar conditions on rare occasions.
What it measures: Compares jawline contour points and chin position against the midline. Detects masseter muscle volume differences and mandibular asymmetry.
Common causes of asymmetry: Masseter hypertrophy from one-sided chewing, jaw clenching or bruxism affecting one side, mandibular development differences (skeletal — not correctable with exercise), TMJ dysfunction.
Jaw symmetry is the most intervention-responsive of the five for most people, since masseter hypertrophy from one-sided chewing builds up over years and reverses with deliberate balanced chewing. For the broader picture, see how to improve your jawline naturally.
Photo conditions strongly affect the score. Following these tips gives the most reliable measurement of your true bilateral symmetry.
Front-facing, neutral expression
Smiling activates your dominant muscles and exaggerates asymmetry. Use a neutral, relaxed expression for the most accurate baseline.
Hair pulled back
Hair covering the forehead or jaw outline blocks landmark detection. Tie hair back so the full face contour is visible.
Even, soft lighting
Side lighting creates shadows that mimic asymmetry. Use diffused front lighting — natural daylight from a window works well.
Camera at eye level
Tilted camera angles distort facial proportions. Keep the camera level with your eyes and roughly arm's length away.
No glasses, hats, or heavy makeup
Glasses obscure eye landmarks. Heavy contouring can shift the apparent jaw and cheekbone outlines.
Most asymmetry has a cause that can be identified and, in many cases, addressed. The best intervention depends on which type dominates your score.
Muscular asymmetry — the most common type
Caused by habitual chewing, sleeping, or expression patterns. Responds to targeted facial exercises with extra reps on the weaker side. The Northwestern face yoga study (JAMA Dermatology, 2018) measured significant improvements over 8–20 weeks. See the 7 evidence-based exercises →
Habitual patterns making it worse
One-sided sleeping, chewing, phone holding, and resting your chin on a hand all create cumulative asymmetry. Even the best exercise routine is undermined if these continue. Habits to fix →
Volumetric or skeletal asymmetry
If asymmetry is visible at rest with neutral expression and shows up clearly in the bone structure (jaw deviation, uneven cheek depth), exercises alone won't resolve it. Dermal fillers address volumetric differences; orthognathic surgery is the option for skeletal asymmetry. Consult a maxillofacial specialist for a structural assessment.
Most people score between 70 and 85 on this scale. Scores of 80 or above are considered good — the face reads as balanced and any asymmetry is subtle. Scores of 90+ are uncommon and indicate near-perfect bilateral symmetry. Note that very high symmetry isn't necessarily more attractive than a balanced 80-range score; some research suggests a small amount of asymmetry actually reads as more natural and trustworthy than perfect symmetry.
This is the Mere Exposure Effect, a well-established psychological phenomenon. You see your mirrored reflection thousands of times and develop a strong preference for that reversed version of your face. When you see an unflipped photograph — which shows your face as others actually see it — asymmetries appear on the 'wrong' side compared to what you expect, making them seem worse than they are. Friends and family tend to prefer the unflipped photo because that's the version of your face they recognize.
No human face is perfectly symmetric. Even faces widely considered the most attractive — including those that score highest on facial harmony tests — have measurable bilateral differences. 3D facial scan studies have found that the right side of the face tends to be marginally larger than the left in most people. Asymmetry below approximately 3% is typically imperceptible to observers in normal conversation (the Farkas standard), and most attractive faces fall in the 80–90 score range rather than at 100.
Symmetry is one factor in perceived attractiveness, but it's not the only one — and beyond a certain threshold, more symmetry doesn't continue to add appeal. Other strongly correlated factors include facial proportions (the relationships between thirds and fifths of the face), sexual dimorphism (gender-typical features), skin quality and texture, and averageness. Studies of perceived attractiveness consistently find that symmetric, average, and feature-typical faces are rated highly, but exceptional attractiveness usually comes from a combination of all three rather than maximum symmetry alone.
It depends on the cause. Muscular asymmetry — the most common type — can be improved with targeted facial exercises, balanced chewing, and breaking habits like one-sided sleeping. The Northwestern University face yoga study (JAMA Dermatology, 2018) found that 30 minutes of daily exercise over 20 weeks measurably increased cheek fullness, which can rebalance muscular asymmetry. Volumetric asymmetry can be partially corrected with fillers. Skeletal asymmetry (bone structure) cannot be changed by exercise and requires orthognathic surgery if treatment is desired.
Crooked smiles are caused by zygomaticus muscle dominance — one side of the muscles that lift the corners of the mouth contracts more strongly or more quickly than the other. This is one of the most common forms of facial asymmetry and is usually a learned neuromuscular pattern rather than a structural difference. Practicing a balanced smile in front of a mirror, holding the contraction evenly on both sides, retrains the pattern over weeks of consistent practice.
Quality depends heavily on the methodology. Tools that map dense facial landmarks — 478 points in the case of MediaPipe Face Mesh — and compare bilateral pairs against a stable midline tend to be more accurate than tools that use a simple mirror-image overlay. Realistic accuracy on clean, front-facing photos is around 80–90%. Accuracy drops sharply with angled photos, partial occlusion, or asymmetric expressions. For best results, use a neutral expression: smiling activates dominant muscle patterns and exaggerates apparent asymmetry.
Bilateral asymmetry has four primary causes. Skeletal differences — the mandible and maxilla developing slightly differently on each side — are usually genetic and stable. Muscular imbalances build up from habits like chewing, sleeping, or resting on one hand. Volumetric differences come from uneven fat distribution and age-related volume loss. Soft tissue differences include skin laxity and habitual expression patterns. Most people have a combination of all four; muscular and habitual causes are the most correctable.