The answer is reliable. A measure is assumed to have a high
reliability if it yields parallel results under steady conditions. It is the
characteristic of a set of test scores that relates to the quantity of
accidental or random error from the measurement procedure that might be rooted
in the scores. Marks that are highly reliable are precise, reproducible, and
constant from one testing time to another. To be exact, if the testing method
were to be repeated with a different group of test takers, fundamentally the
same results would be gotten.
