Spreadsheet Practice

How to calculate RMSE in Excel

Formula (Excel and Google Sheets)

=SQRT(SUMPRODUCT((B2:B7-C2:C7)^2)/COUNT(B2:B7))

Square the errors, average them and take the square root: =SQRT(SUMPRODUCT((B2:B7-C2:C7)^2)/COUNT(B2:B7)).

Result on the example
7.23 in F1
Works in
Every current version
Google Sheets
Same formula

See it work

The formula is already in F1. Change any input and the result updates, or edit the formula to experiment.

How it works

RMSE is "root, mean, square" read backwards. Each error (8, -6, 3, 12, -5, 6) is squared so negatives don't cancel and big misses count more. SUMPRODUCT adds the squares (314), dividing by the count gives the mean, and SQRT brings it back to the original units: about 7.2 units off on average.

=SQRT(SUMPRODUCT((B2:B7-C2:C7)^2)/COUNT(B2:B7))

Result7.234178138

  1. B2:B76 rows × 1 col: 120, 135, 128, 150, …

    A range: 6 cells in one column.

  2. C2:C76 rows × 1 col: 112, 141, 125, 138, …

    A range: 6 cells in one column.

  3. B2:B7-C2:C7{6 rows × 1 col} 8, -6, 3, 12, …

    The - operator subtracts.

  4. B2:B7-C2:C7)^2{6 rows × 1 col} 64, 36, 9, 144, …

    The ^ operator raises to a power.

  5. SUMPRODUCT((B2:B7-C2:C7)^2)314

    SUMPRODUCT: Multiplies arrays row by row and adds the results.

    • array1B2:B7-C2:C7)^2{6 rows × 1 col} 64, 36, 9, 144, …
  6. COUNT(B2:B7)6

    COUNT: Counts cells that contain numbers.

    • value1B2:B76 rows × 1 col: 120, 135, 128, 150, …
  7. SUMPRODUCT((B2:B7-C2:C7)^2)/COUNT(B2:B7)52.33333333

    The / operator divides.

  8. SQRT(SUMPRODUCT((B2:B7-C2:C7)^2)/COUNT(B2:B7))7.234178138

    SQRT: Square root.

    • numberSUMPRODUCT((B2:B7-C2:C7)^2)/COUNT(B2:B7)52.33333333

In Google Sheets

The same formula works in Google Sheets: =SQRT(SUMPRODUCT((B2:B7-C2:C7)^2)/COUNT(B2:B7)). We ran it in Google Sheets mode on the same data and it returns 7.23.

Other ways to do it

Each one was run on the same example sheet.

FormulaResultWhen to use it
=SQRT(AVERAGE((B2:B7-C2:C7)^2))Excel only7.23Excel 365 averages the squared errors directly. Older versions need Ctrl+Shift+Enter; Google Sheets needs ARRAYFORMULA.

Common mistakes

  • Dividing by COUNT-1 instead of COUNT gives a different number. RMSE for forecasts divides by the number of points.
  • Blank forecasts are treated as 0 inside the subtraction and produce huge errors. Keep both columns complete, or filter the rows first.

Try it yourself

Same data, empty answer cell. Your formula is graded instantly, then re-checked on changed data, so a typed-in number won't pass.

Calculate RMSE

In F1, calculate the root mean square error of the forecasts in C2:C7 against the actuals in B2:B7.

Questions

How do I calculate the mean absolute error (MAE)?

Use =SUMPRODUCT(ABS(B2:B7-C2:C7))/COUNT(B2:B7), which gives 6.67 here.

Is there a built-in function?

No single one, but =SQRT(SUMXMY2(B2:B7,C2:C7)/COUNT(B2:B7)) uses SUMXMY2, which adds the squared differences of two ranges.

Checked by running on 2026-10-30: every formula and result on this page was calculated by the Spreadsheet Practice formula engine, in both Excel and Google Sheets modes.