Objective: Self-report symptom inventories are commonly used in adult ADHD assessment, and research indicates they should be interpreted with caution. This study investigated one self-report symptom inventory for adult ADHD in a clinical sample. Method: Archival data were used to evaluate diagnostic utility of the Conners Adult ADHD Rating Scale--Self-Report: Long Version (CAARS-S:L) in a sample of 122 adults seeking ADHD assessment. Results: Overall, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) estimates for the ADHD Index and other CAARS-S:L scales demonstrated weak accuracy. Anxiety and depression were the most common diagnoses present when a false positive on the ADHD Index was observed. PPV and specificity for the ADHD Index were higher in males compared to females. Conclusion: The CAARS-S:L may be useful for screening purposes in some cases, but should not be the main method used for diagnostic purposes. Clinical implications of findings are discussed.