A randomized, double-blind, placebo-controlled, parallel-group study was conducted to evaluate the efficacy and safety of gabapentin in relieving the symptoms of social phobia. Sixty-nine patients were randomly assigned to receive double-blind treatment with either gabapentin (dosed flexibly between 900 and 3,600 mg daily in three divided doses) or placebo for 14 weeks. A significant reduction (p < 0.05) in the symptoms of social phobia was observed among patients on gabapentin compared with those on placebo as evaluated by clinician- and patient-rated scales. Results were similar for the intent-to-treat and week-2 completer populations. Adverse events were consistent with the known side effect profile of gabapentin. Dizziness (p = 0.05), dry mouth (p = 0.05), somnolence, nausea, flatulence, and decreased libido occurred at a higher frequency among patients receiving gabapentin than among those receiving placebo. No serious adverse events or deaths were reported. On the basis of these limited data, it seems that gabapentin offers a favorable risk-benefit ratio for the treatment of patients with social phobia. Further studies are required to confirm this effect and to determine whether a dose-response relationship exists.