The objective of this study was to evaluate the ear tag based accelerometer SMARTBOW (Smartbow, Weibern, Austria) for detecting rumination time, chewing cycles and rumination bouts in dairy cows. For this, the parameters were determined by analyses of video recordings as reference and compared with the results of the accelerometer system. Additionally, the intra- and inter-observer reliability as well as the agreement of direct cow observations and video recordings was tested. Ten Simmental cows were equipped with 10 Hz accelerometer ear tags and kept in a pen separated from the other herd mates. During the study, cows’ rumination and other activities were directly observed for 20 h by 2 trained observers. Additionally, cows were video recorded, 24 h a day. After exclusion of unsuitable videos, 2,490 h of cow individual 1-hour video sequences were eligible for further analyses. Out of this, 100 video sequences were randomly selected and analyzed by a trained observer using professional video analyses software. Based on these analyses, half of the data were used for development and testing of the SMARTBOW algorithm, respectively. Inter-and intra-observer reliability as well as the comparison of direct against video observations revealed in high agreements for rumination time and chewing cycles with Pearson correlation coefficients of r > 0.99. The rumination time, chewing cycles as well as rumination bouts detected by SMARTBOW were highly associated (r > 0.99) with the analyses of video recordings. Testing the algorithm revealed in an underestimation of the average ± standard deviation (SD) rumination time per 1-hour period by SMARTBOW of 17.0 ± 35.3 s (i.e. ‑1.2%), compared with visual observations. The average number ± SD of chewing cycles and rumination bouts was overestimated by the SMARTBOW system by 59.8 ± 79.6 (i.e. 3.7%) and by 0.5 ± 0.9 (i.e. 1.8%), respectively compared with the video analyses. From a practical and clinical point of view, the detected differences were negligible.