In the present world, there are many two-stage systems which provide information of inputs, outputs and intermediate measures which are imprecise, such as, (stochastic, fuzzy, interval etc). In these conditions, a two-stage data envelopment analysis or a (two-stage DEA method) cannot evaluate the e, ciencies of these systems. In several two-stage systems, the simultaneous presence of stages is necessary for the , nal product. Hence, in this paper, we shall propose the stochas-tic multiplicative model and the deterministic equivalent, to measure the e, ciencies of these systems, primarily, in the presence of stochastic data, under the constant returns to scale (CRS) assumption, by using the non-compensatory property of the multiplication operator. Then, we will use the reparative property of the additive operation to propose the additive models as well as the deterministic equivalents, to calculate the e, ciencies of two-stage systems, in presence of stochastic data, under the constant returns to scale (CRS) and variable returns to scale (VRS) assumptions. This is to illustrate that a simultaneous presence of the stages is not necessary for the , nal product and one stage compen-sates the shortcomings of another stage. Likewise, we shall convert each of these deterministic equivalents to quadratic programming prob-lems. Based on the proposed stochastic models, the whole system is e, cient if and only if, the , rst and the second stages are e, cient. Ul-timately, in the proposed multiplicative model, we will illustrate the proposed multiplicative model, by employing the data of the Taiwanese non-life insurance companies, which has been extracted from the extant literature.