Traditionally, timing and the failure rate are the only two factors considered in software reliability formula, which is actually incomplete. Reliability should be redefined as a function of software complexity, test effectiveness, and operating environment. This paper focuses on software complexity with its relation to the software reliability. Today, many software complexity measurements have been proposed, but most of them treat the reliability model incompletely. This paper proposes a new method which considers a relatively complete view of software reliability including its complexity and test effectiveness of the software being tested.