Abstract The total reliability of a mine searching system is driven by the triple of intrinsic capability, which describes the physical-technical basis capability, the application and environmental factors and the human factors. Some of them can be determined in laboratory measurements but the human factor and a part of environment conditions and their interaction with the device need to be treated statistically. That is why the test & evaluation procedure described in CEN CWA 14747:2003, includes in addition to parameter tests of metal detectors also the reliability or blind field tests under local conditions with local personnel. A series of three big field trials had been accomplished in the ITEP-project 2.1.1.2 “Reliability Model for Test & Evaluation of Metal Detectors” to specify the optimum conditions for reliable trial results with affordable effort. For each set of specific working conditions, characterized in terms of a combination of one mine type in one soil with one detector handled by local personnel, the searching system will show up a working performance in mine detection rates as a function of mine depth and show up a certain overall false call rate. During the ITEP-trials in Benkovac and Oberjettenberg the authors learnt to determine this function separately for each mine type in each soil, which is especially important for low metal mines in uncooperative soil which will be illustrated for the mine PMA2 in different types of soil. The question of representativeness for field conditions on the one hand and necessary statistical set up for the possibility to distinguish between individual detector performances is still under discussion.