Several studies report observations of orbital cyclicity in seismic reflection data as distinct power spectral peaks that align with Milanković periodicities. It remains unclear, however, if hypothesis testing for orbital forcing using seismic data can be performed with statistical power comparable to directly sampled data, such as outcrop, drill core or borehole logs. In this study we aim to quantify this using Monte Carlo ensemble modelling to compare seismic and borehole log cyclostratigraphy. We develop a method for spectral background estimation that accounts for some of the amplitude and frequency effects inherent to seismic data. We then forward model the seismic response of an ensemble of models where the acoustic impedance approximates red noise, with and without an injected orbital signal from an astronomical solution. We demonstrate two examples: i) a simplified model with constant background velocity, constant sedimentation rate and a parametric seismic source wavelet, and ii) a real-world example based on ODP Site 1084 (Cape Basin). We observe that the sensitivity and specificity for the seismic case are strongly frequency-dependent, compared to the largely frequency-independent results for the borehole log cyclostratigraphy. For the real-world data example, we observe a spectral peak corresponding to 95 kyr eccentricity cyclicity with an uncalibrated confidence level of >95 %. Our Monte Carlo ensemble modelling, however, shows that the false positive rate at this frequency and confidence level is around 25 %, compared to around 5 % for the equivalent borehole log cyclostratigraphy. We also demonstrate short-period eccentricity modulation and bundling analysis applied to the seismic data, which is able to successfully invert for the model sedimentation rate for the simplified synthetic example. These results suggest that reliably identifying Milanković cycles from seismic reflection data is strongly dependent on the site geology, the geophysical parameters and the spectral frequency in question. Seismic examples should ideally be “ground truthed” against positive evidence of orbital cyclicity from a nearby borehole. In such cases, seismic data can be used to extrapolate borehole cyclostratigraphy data both laterally between boreholes and vertically beyond the maximum drilled depth. We suggest that sediment drifts are the sedimentary environment that is most promising for the detection of orbital cyclicity in seismic reflection images, and similar principles could also be applied to other geophysical reflection methods such as sub-bottom profilers.