Statement of problem: Major objective in making on implant-supported prosthesis is the production of superstructure that exhibits a passive fit when connected to multiple abutments. One requirement to ensure passive fit is to make an accurate impression. Purpose : The purpose of this study was to compare the accuracy of master cast fabricated by using different impression methods at the different impression levels. Material and method: The master model used in this study was resin block having low implant analogs. Impression method studied were 1) direct method on fxiture level (Group FIX-D), 2) indirect method on fixture level(Group FIX-I), 3) modified indirect method on fixture level(Group FIX-M), 4) direct method on abutment level(Group AB-D) and 5) indirect method on abutment level(Group AB-I). Each of the five groups took 10 impressions. Fifty impressions were made for master cast by using Impregum $F^{(R)}$ impression material loaded on individual tray. Three dimensional measuring microscope was used to measure the inter-implant distance. Error rate of each inter-implant distance were calculated and evaluated. Results : The results were as follows. 1. Group FIX exhibited higher accuracy than group AB. 2. In group FIX, modified indirect method showed the highest accuracy, while indirect method showed the lowest accuracy. In group Ab, indirect method showed the higher accuracy than direct method. 3. Group FIX showed larger horizontal error than group AB. But, group AB showed the larger vertical error than group FIX. 4. Group Fix-M showed smallest vertical and horizontal error. Conclusion: An impression method have more effect on accuracy of master model than an impression level. A modified indirect method showed smallest vertical and horizontal error.