The trend of modern high-end CNC equipment with high reliability and long life expectancy makes traditional methods of equipment reliability assessment difficult due to the multiple performance parameters as well as less failures and degradation data. This paper proposes a performance reliability assessment based on parameter degradation data, which deals with reliability evaluation with small numbers of samples. With the analysis of performance degradation processes and rules, the framework of the performance reliability assessment for parameters is proposed. According to the degradation data of a single performance parameter, the degradation trajectory of the performance parameters is curve fitted by Support vector machines (SVM). The reliability when the degradation curve reaches its specified threshold is calculated. The probability density function at time is also built, which describes the shape of the failure distribution of each performance parameter at each stage in time. Finally, using a specific type of CNC machine tool as an example, the performance reliability assessment method is verified.