To determine patterns of and trends in contributions to central nervous system (CNS) polypharmacy, defined by the Beers Criteria as three or more CNS-active medications of each medication class, of adults aged 65 and older seen in U.S. outpatient medical practices. National Ambulatory Medical Care Survey (2004-2013). U.S. outpatient medical care. Visits by older adults to outpatient physicians (N = 97,910). Visits including three or more CNS medications including antipsychotics, benzodiazepines, nonbenzodiazepine benzodiazepine receptor agonist hypnotics (NBRAs), tricyclic antidepressants (TCAs), selective serotonin reuptake inhibitors (SSRIs), and opioids. The proportion of CNS polypharmacy that each medication class contributed during 2011 to 2013 was determined, and then logistic regression was used to determine trends from 2004 to 2013 in the contribution of individual medication classes to such polypharmacy. Of recent CNS polypharmacy visits, 76.2% included an opioid, and 61.8% included a benzodiazepine; 66.0% of the polypharmacy visits with benzodiazepines included opioids, and 53.3% of the polypharmacy visits with opioids included benzodiazepines. Between 2011 and 2013, opioid and benzodiazepine co-prescribing occurred at approximately 1.50 million visits (95% confidence interval (CI) = 1.23-1.78 million) annually. From 2004 (reference) to 2013, the proportion of polypharmacy visits with opioids rose from 69.6% to 76.2% (adjusted odds ratio = 2.15, 95% CI = 1.19-3.91, P = .01), and the corresponding proportion that included benzodiazepines fell. Of the polypharmacy visits, the odds of SSRI, NBRA, and antipsychotic use were unchanged, and that of TCAs decreased. In older adults, opioid use appears to be largely driving the recent national increase in CNS polypharmacy. Although concomitant use of opioids and benzodiazepines is associated with greater mortality, they are the most common contributors to CNS polypharmacy in older adults.