Motor-evoked potentials (MEPs) vary in size from one stimulus to the next. The objective of this study was to determine the cause and source of trial-to-trial MEP size variability. In two experiments involving 10 and 14 subjects, the variability of MEPs to cortical stimulation (cortical-MEPs) in abductor digiti minimi (ADM) and abductor hallucis (AH) was compared to those responses obtained using the triple stimulation technique (cortical-TST). The TST eliminates the effects of motor neuron (MN) response desynchronization and of repetitive MN discharges. Submaximal stimuli were used in both techniques. In six subjects, cortical-MEP variability was compared to that of brainstem-MEP and brainstem-TST. Variability was greater for MEPs than that for TST responses, by approximately one-third. The variability was the same for cortical- and brainstem-MEPs and was similar in ADM and AH. Variability concerned at least 10-15% of the MN pool innervating the target muscle. With the stimulation parameters used, repetitive MN discharges did not influence variability. For submaximal stimuli, approximately two-third of the observed MEP size variability is caused by the variable number of recruited alpha-MNs and approximately one-third by changing synchronization of MN discharges. The source of variability is most likely localized at the spinal segmental level.