Flexural strength test has a significant effect on the determination of failure strengths and cracking moment. According to ASTM-C78, the size and shape of used specimens were cubes by size (700*150*150 mm). Here, the efficiency of the non-destructive Break-Off (BO) and flexural strength tests was investigated for assessing the in-place compressive strength of steel fiber reinforced concrete (SFRC). In order to provide a thorough and comprehensive database, 24 mixtures were designed with various cement content, maximum aggregate size, steel fibre volume fractions and the constant water/ cement ratio of 0.4 for all mixtures. Then, effective parameters of SFRC and Break-Off and flexural strength test results were evaluated. The studies showed that volumetric percentage and features of steel fibers had a significant influence on concrete properties as well as Break-Off and flexural strength test results. According to the experimental results it could be generally concluded that the influencing factors, namely, SFRC properties due to presence of steel fibers and non-destructive tests significantly affect the results as follows: Generally, for a constant W/C ratio, it can be concluded that raising the cement content increases the mean values of Break-Off strength and Flexural strength. It can be stated that increasing the size of the aggregate causes an increase in strength. Also, the steel fibers restrain the development of internal micro-cracks in the concrete and thus contribute to the increase in bending strength, which causes improving Break-Off and flexural strengths. In addition, the conventional numerical regression model was developed in this study. Statistical indices were used to compare the efficiency and accuracy of the model. The result of this study confirmed the accuracy of the artificial neural network models in the determination of the compressive strength of concrete.