The mechanical properties of fibre‐reinforced thermoplastics and their dependencies on the manufacturing process, fibre properties, fibre concentration and strain rate have been researched intensively for years in order to predict their macroscopic behaviour by numerical simulations as precisely as possible. Including the microstructure in both real and virtual experiments has improved prediction precision for injection‐moulded glass fibre‐reinforced thermoplastics significantly. In this work, we apply three established methods for characterisation and modelling to an injection‐moulded and to a 3D printed material. The geometric properties of the fibre component as fibre orientation, fibre length and fibre diameter distributions are identified by analysing reconstructed tomographic images. For comparing the fibre lengths, a recently suggested new method is applied. Based on segmentations of the tomographic images, we calculate the elastic stiffness of both composites numerically on the microscale. Finally, the mechanical behaviour of both materials is experimentally characterised by micro tensile tests. The simulation results agree well with the measured stiffness in case of the injection‐moulded material. However, for the 3D printed material, measurement and simulation differ strongly. The prediction from the simulation agrees with the values expected from the image analytic findings on the microstructure. Therefore, the differences in the measured behaviour have to be contributed to the matrix material. This proves demand for further research for 3D printed materials for predictable prototypes, preproduction series and possible serial application.