The reflectance properties of facial hair and skin across sexes produce different degrees of red and green in male (more red) and female (more green) faces. Consequently, measuring the overall ratio of red/green energy in a face is sufficient for accurate sex classification. The optimal red/green threshold for discriminating 200 Caucasian faces by sex yielded an accuracy rate of 75% correct with a d' of 2.0 Faces had no makeup and were edited to remove all hair around the head. A second set of Caucasian faces produced similar results. Preliminary analyses suggest that the red/green ratio is also sufficient for sex classification of Asian and African faces. In contrast, pre-pubescent Caucasian faces were classified at chance. Thus, the red/green difference between males and females may be attributed to post-puberty sexual dimorphism in the spectral properties of human faces. We compared these computational findings with the human ability to discriminate male faces from females faces. To prevent observers from relying on shape information useful for sex classification, the 200 Caucasian faces were dramatically blurred using a Gaussian filter. Faces were presented for 100ms and observers simply judged whether each face was male or female. For female faces there was a -0.66 correlation between red/green ratio and accuracy in sex classification; for males the correlation was +0.42. Reinforcing the relationship between our model and human performance, observers were at chance in their ability to discriminate pre-pubescent faces. Our results may provide a mechanism for rapid sex classification through the differential response of early color opponent processes to male and female faces. In sum, red/green energy appears to be a reliable cue for fast and accurate discrimination of faces by sex.