This paper presents a new fuel cycle benchmarking analysis methodology by coupling Gaussian process (GP) regression, a popular technique in machine learning, to dynamic time warping, a mechanism widely used in speech recognition. Together, they generate figures of merit (FOMs) for a suite of fuel cycle realizations. The FOMs may be computed for any time series metric that is of interest to a benchmark. For a given metric, these FOMs have the advantage that they reduce the dimensionality to a scalar and are thus directly comparable. The FOMs account for uncertainty in the metric itself, utilize information across the whole time domain, and do not require that the simulators use a common time grid. Here, a distance measure is defined that can be used to compare the performance of each simulator for a given metric. Additionally, a contribution measure is derived from the distance measure that can be used to rank order the impact of different partitions of a fuel cycle metric. Lastly, this paper warns against using standard signal-processing techniques for error reduction, as error reduction is better handled by the GP regression itself.