Z Score Calculator (Percentile & T-Score)
Free Z score calculator that finds the Z-score, T-score, and percentile rank from a score, mean, and standard deviation, or works backward from a target percentile.
What is a Z-score / T-score calculation?
This tool calculates the Z-score (standard score) and T-score of a test result, showing where that score sits within a group based on the score, the mean, and the standard deviation. The Z-score measures how many standard deviations a value is from the mean, while the T-score is a common linear transformation of the Z-score — multiplying it by 10 and adding 50 — that turns those often-negative, decimal Z-scores into an easy-to-read number centered on 50. A T-score of 50 means the result is exactly average, and a T-score of 60 means it is one standard deviation above average.
Instead of entering a score, you can also enter a target percentile (for example, 90 if you want to know what score puts you in the top 10%) to work backward and find the score that corresponds to it. Because this calculation assumes a standard normal distribution, it is most accurate when the underlying scores are roughly normally distributed. If you do not know the mean and standard deviation of the group, you can also paste in a list of raw scores and have them calculated automatically.
How to use the Z-score calculator
- Choose a calculation mode Pick "Calculate from a score" if you want the Z-score and T-score for a score you already have, or "Work backward from a percentile" if you want to know the score required to reach a target rank.
- Enter the mean and standard deviation Enter the mean and standard deviation of the test. If you do not know these values, use the "auto-calculate from raw scores" tool below.
- Enter the score or target percentile Depending on the mode you chose, enter either the score you want to evaluate or the target percentile (0-100).
- Check the results The Z-score, T-score, and percentile rank (or their inverse) are recalculated automatically as soon as you change any input.
Tips for getting more out of it
- The T-score is simply "Z-score x 10 + 50." A T-score of 60 corresponds to a Z-score of 1.0, and a T-score of 40 corresponds to a Z-score of -1.0.
- If you do not know the mean and standard deviation, paste the scores of everyone in the group into the "auto-calculate from raw scores" section below and they will be calculated for you.
- The percentile-to-score mode is handy when you want to know "what score do I need to be in the top 10%?" Just enter 90 as the target percentile.
- This calculation assumes the scores are roughly normally distributed. Accuracy drops if the number of test-takers is very small or the scores are heavily skewed.
- The two-tailed probability represents the chance of seeing a result at least this far from the mean purely by chance, which is the same idea behind a p-value in statistical hypothesis testing.
Ways to use this Z-score calculator
Analyzing practice test or exam results
Enter your score along with the class mean and standard deviation to quickly see how far you are from the T-score you are aiming for.
Comparing against an admissions or cutoff target
Enter a target percentile (say, the top 20%) to work backward and estimate the score you will need to reach.
Checking where a measurement falls in quality control data
Use the Z-score to see where a single measurement falls within the overall distribution of inspection or production data, expressed as a percentile.
Statistics coursework and lab reports
Convert between Z-values and percentiles under the standard normal distribution without doing the math by hand or looking up a statistical table.
Z-score and T-score glossary
- Z-Score
- A measure of how many standard deviations a score is from the mean. It is calculated as (score - mean) / standard deviation, giving 0 at the mean, a positive value above it, and a negative value below it.
- T-Score
- A rescaled version of the Z-score calculated as "Z x 10 + 50." A T-score of 50 represents the mean, and one standard deviation above the mean (Z=1) corresponds to a T-score of 60, making test results easier to read at a glance.
- Standard normal distribution
- A normal distribution that has been standardized to have a mean of 0 and a standard deviation of 1. Score distributions on many exams are assumed to roughly follow this shape, which is what allows Z-scores to be converted into percentiles.
- Percentile
- A measure of where a value falls when data is sorted from smallest to largest, expressed as the percentage of values at or below it. The 90th percentile means that 90% of the group scored at or below that value.
- Population standard deviation
- The standard deviation calculated across an entire group, found by taking the square root of the average of the squared differences between each value and the mean. For T-score calculations, it is standard practice to treat everyone who took the test as the population.
- Two-tailed probability
- The combined probability of obtaining a value at least as far from the mean in either direction — both higher and lower — as the observed score.
Frequently asked questions
Side Note — where does the T-score idea come from?
The underlying idea of the T-score — rescaling a Z-score into a friendlier number centered on 50 — has long been used in psychometrics and standardized testing to make relative performance easier to communicate than raw Z-scores, which are often negative decimals.
In Japan, this same transformation is known as "hensachi" and became a fixture of the education system in the 1960s. It is often credited to Shozo Kuwata, an educator and cram-school instructor who wanted a way to describe a student's ability not just by a raw score, but by their relative standing within the group that took a particular practice exam. Before then, guidance counselors mostly relied on class rank alone, which made it hard to compare results across practice exams of differing difficulty.
The Z-score that both the T-score and hensachi are built on traces back to the standardization techniques formalized by statisticians such as Karl Pearson in the late 19th century — a way to compare data with different units and different means on a single, common scale of "distance from the mean." The technique is now used widely, from psychological testing to medicine to quality control. Japan's hensachi can be thought of as a local, education-focused packaging of this same general-purpose idea, using easy-to-remember numbers: 50 for average, and 10 points per standard deviation.
Because a T-score (or hensachi) always reflects standing relative to the specific group that took a given test, the same raw score can produce a different T-score depending on who else took it. A test taken mostly by students aiming for highly selective universities will tend to produce lower T-scores for a given raw score, while a test taken by a broader range of students will tend to produce higher ones. Whenever you compare T-scores across different tests, it is worth remembering which group and which exam they are actually describing.