RMSE Calculator

Root mean squared error (RMSE) is the square root of MSE, which brings the error back into the same units as the target variable — dollars, degrees, or whatever you are predicting. It penalizes large errors like MSE but is directly interpretable. Paste one "actual, predicted" pair per line.

One pair per line: actual value, then predicted value — e.g. "3, 2.5".

Result

Enter your values and press Calculate — the result appears here.

Worked examples

Small errors

  • pairs = 3, 2.5 -0.5, 0 2, 2 7, 8

Result: RMSE 0.6124 (MSE 0.375)

Perfect predictions

  • pairs = 10, 10 20, 20 30, 30

Result: RMSE 0

Frequently asked questions

Why report RMSE instead of MSE?

MSE is in squared units (e.g. dollars squared), which are hard to interpret. RMSE takes the square root, putting the error back in the original units — an RMSE of 0.61 means predictions are off by about 0.61 units on average.

How does RMSE compare with MAE?

RMSE is always ≥ MAE for the same data (by Jensen's inequality), and the gap grows with the size of the worst errors. RMSE punishes large errors more than MAE does, so a big difference between them signals heavy-tailed errors or outliers.

What is a good RMSE?

It depends entirely on the scale of your target variable — an RMSE of 5 is great when values are in the hundreds and terrible when they range 0–10. Compare RMSE against the mean or standard deviation of the actual values, or against a baseline model.

Copied!