Background Immune checkpoint inhibitors (ICIs) have transformed treatment for melanoma, but identifying reliable biomarkers of response and effective modifiable lifestyle factors has been challenging. Obesity has been correlated with improved responses to ICI, although the association of body composition measures (muscle, fat, etc) with outcomes remains unknown. Methods We performed body composition analysis using Slice-o-matic software on pretreatment CT scans to quantify skeletal muscle index (SMI=skeletal muscle area/height 2), skeletal muscle density (SMD), skeletal muscle gauge (SMG=SMI × SMD), and total adipose tissue index (TATI=subcutaneous adipose tissue area + visceral adipose tissue area/height 2) of each patient at the third lumbar vertebrae. We then correlated these measures to response, progression-free survival (PFS), overall survival (OS), and toxicity. Results Among 287 patients treated with ICI, body mass index was not associated with clinical benefit or toxicity. In univariable analyses, patients with sarcopenic obesity had inferior PFS (HR 1.4, p=0.04). On multivariable analyses, high TATI was associated with inferior PFS (HR 1.7, p=0.04), which was particularly strong in women (HR 2.1, p=0.03). Patients with intermediate TATI and high SMG had the best outcomes, whereas those with low SMG/high TATI had inferior PFS and OS (p=0.02 for both PFS and OS). Conclusions Body composition analysis identified several features that correlated with improved clinical outcomes, although the associations were modest. As with other studies, we identified sex-specific associations that warrant further study.