Facial composites are crucial in the criminal justice system. In this archival study, we investigated the assumption that the success of facial composites depends partly on variables related to the crime, which either impairs or facilitates mnemonic processes. When a facial composite is successful in taking an offender to court it is sometimes archived as a positive facial composite, including a photo of the culprit and information about the crime. A total of 88 positive facial composites were investigated. The accuracy of facial composites was tested as a function of five variables related to the crime: type of crime, presence of weapon, retention interval, exposure duration, and disguise. Participants judged the resemblance of the perpetrators' photo with their correspondent facial composite. The results pointed out that only exposure duration was significantly associated with facial composites accuracy. Possible implications and future directions for research using archived facial composites are discussed.