Browse all 103 browser-based tools (103 currently marked free), or tell us what useful utility we should build next.
Calculate mean, median, mode, range, count, and sum from a list of numbers. Compare the summaries instead of relying on one average alone.
All parsing and math run locally in your browser — pasted data is never uploaded.
Count, sum, mean, median, mode(s), min, max, and range from one paste — with the substituted formula shown beside each result.
Multimodal data lists every tied value; when all values occur equally the tool says “no meaningful mode” instead of inventing one.
Commas, spaces, tabs, and newlines — any combination. Stray separators are ignored; non-numeric tokens are named so you can fix them.
Parsing and statistics run locally in your browser. Pasted data is never uploaded and never reaches page analytics.
This statistical calculator computes arithmetic mean, median, mode, range, sum, and sample count simultaneously from a pasted numeric dataset. The mean uses all values and can move substantially when an outlier is added. The median describes the middle of the ordered data, and the mode identifies repeated values. Check the input list and missing-value treatment before interpreting any summary.
These are the classic measures of location. The NIST/SEMATECH e-Handbook §1.3.5.1 defines them precisely: the mean is the sum divided by the count (Σxᵢ / n); the median is the point with half the data smaller and half larger; the mode is the most frequent value, “not necessarily unique.” OpenStax's Introductory Statistics 2e §2.5 adds the practical rule: the median is generally better when extreme values or outliers are present.
This calculator follows those definitions exactly. Sorting is numeric, never alphabetical. For even counts the median interpolates between the two middle values per the standard formula ((Y₂ + Y₃)/2 in a four-point set). And the mode is reported honestly: ties list every winner, while datasets where everything occurs equally often get “no meaningful mode” instead of a fabricated answer.
| Measure | Formula / rule | Worked example on [2, 3, 3, 5, 14] |
|---|---|---|
| Mean | Σxᵢ ÷ n | 27 ÷ 5 = 5.4 |
| Median | middle of sorted n; even n → average of the two middles | sorted [2,3,3,5,14] → 3 |
| Mode | value(s) with the highest frequency | 3 (appears 2×) |
| Range | max − min | 14 − 2 = 12 |
Outlier demo · [2, 3, 3, 5, 14]
count 5 · sum 27 · mean 5.4 · median 3 · mode 3 · min 2 · max 14 · range 12
The single 14 pulls the mean up to 5.4 — above four of the five actual values — while the median holds at 3. Classic case for trusting the median.
Multimodal · [1, 2, 2, 3, 3]
modes 2 and 3 (appearing 2× each) · mean 2.2 · median 2
Fully tied · [4, 4, 9, 9]
no meaningful mode — all distinct values occur 2× equally · mean 6.5 · median 6.5
Edge cases · separators, blanks, bad tokens
"10,,20 30" parses cleanly to three values (empty tokens dropped). A stray word like "10, abc, 30" returns an error naming “abc” specifically instead of skipping it silently, because a silent skip would quietly change every statistic downstream.
Mean and median always exist. The mode is different: many textbook calculators quietly print the first value they happen to encounter when frequencies tie, which manufactures a “most common value” that isn't real. This tool separates the three honest outcomes — a genuine winner, several tied winners listed together, or no mode at all — and tells you which case you're in, including the frequency that decided it.
Numeric parsing is strict too: Number.isFinite rejects Infinity and empty strings alike, because a single infinite value would poison the sum and mean for everything else in your list. Decimals and negatives are fine — -2.5 sorts exactly where it belongs.
Your dataset never leaves your device. Tokenizing, sorting, frequency counting, and formatting all happen in local JavaScript — no uploads, tool input is not sent to Toolk. Toolk's page-view analytics count visits but never receive anything you paste here. I hand-checked the shipped math before publishing: [2, 3, 3, 5, 14] returns mean 5.4, median 3, mode 3, range 12; the even-count case [1, 2, 3, 4] interpolates to a median of 2.5; mixed-separator input parses correctly; and non-numeric tokens come back named in the error.
Percent of, change, increase & decrease
GPA CalculatorWeighted grade averages by credit
Tip CalculatorSplit bills evenly across a party
Sales Tax CalculatorForward and reverse percent tax math
Discount CalculatorSale prices for stacked discounts
Loan CalculatorAmortized payments month by month
Compound Interest CalculatorGrowth compounding over years
Unit ConverterLength, weight, volume & temperature
Number Base ConverterBinary, hex, octal & decimal
Timestamp ConverterEpoch seconds to readable dates
Word CounterWord, character & sentence counts
All ToolsBrowse the full free toolkit hub
Last updated: September 15, 2026 · Runs 100% in your browser — no uploads, tool input is not sent to Toolk.
Use the mean when your data is roughly symmetric with no extreme outliers; it uses every value. Use the median when outliers or skew exist, because a single huge value drags the mean but not the middle rank — the NIST statistics handbook recommends the median for heavy-tailed data. Use the mode for categorical-style questions like “which size sells most?”.
Honestly. If two values tie for the highest frequency both are listed (e.g. [1, 2, 2, 3, 3] reports modes 2 and 3). If every distinct value shares the same frequency — say [4, 4, 9, 9] where each appears twice — the tool reports no meaningful mode rather than arbitrarily picking one, matching how statisticians treat fully tied data.
With an even count there is no single middle value, so the tool averages the two central values of the sorted dataset: for [1, 2, 3, 4] that is (2 + 3) ÷ 2 = 2.5. The result is flagged as interpolated because 2.5 may not be one of your actual observations — useful context when reporting survey medians.
No. Tokenizing, sorting, and every statistic run as plain JavaScript inside your browser tab; nothing you paste leaves your device. Toolk's page analytics count visits to the page itself but never receive your dataset, so the tool also keeps working offline once loaded.