There are many IRT models for available for realistic work which are adaptive to different datas. In china, there exits many kinds of examinations, and the item types are rich. In realistic work, only one IRT model can not reflect all data’s features. Thus one more IRT models are considered called mixture model to realize the optimized data fit. This paper explored the idea, principle, parameter estimation and the properties of mixture model based on 3PLM and GRM. To explore the parameters estimation precision, and to probe the properties of mixture model, Monte Carlo method was used here. The result showed: (1) The parameters estimation precision of Mix_Tu program was preferably great, which equivalent to the precision of Parscale program. (2) When “item bugs”, the estimating of parameter b and c with Mix_Tu program were more affected by the extent of item bugs than that with Parscale program, the estimating of parameter a was vice versa, while the estimating of theta was similar. (3) When “examination bugs”, the estimating of all parameters with Mix_Tu program were less affected by the degree of examination bugs than that with Parscale program. The estimating was more robust than that with Parscale program.