Confidence is an adaptive computation when environmental feedback is absent, yet there is little consensus regarding how perceptual confidence is computed in the brain. Difficulty arises because confidence correlates with other factors such as accuracy, response time (RT), or evidence quality. We investigated whether neural signatures of evidence accumulation during a perceptual choice predict subjective confidence independently of these factors. Using motion stimuli, a central-parietal EEG component (CPP) behaves as an accumulating decision variable that predicts evidence quality, RT, accuracy, and confidence (Experiment 1). Psychophysically varying confidence while holding accuracy constant (Experiment 2), the CPP still predicts confidence. Statistically controlling for RT, accuracy, and evidence quality (Experiment 3), the CPP still explains unique variance in confidence. The results indicate that evidence accumulation, indexed by the CPP, is tightly linked to the subjective perceptual experience of sensory information. Independent of other factors, pre-decision neural signatures of evidence accumulation encode subjective confidence.