The use of parallel communication paths to provide reliable, low-latency service is a significant trend in cellular networks, as it can provide a way to satisfy the exacting Quality of Service (QoS) requirements of 5G-enabled applications. In particular, coding data across multiple paths can significantly improve reliability and reduce overall latency, compensating for stragglers and lost packets with the redundant information from other paths. However, the design trade-offs in optimizing these systems are non-trivial, particularly when considering Age of Information (AoI). In this work, we derive the latency and Peak Age of Information (PAoI) distributions for such a multipath coded system, drawing design insights on how to optimize either. While preemption is always the optimal choice to minimize AoI in a single-path, uncoded queuing system, the trade-off in this case is more complex, as dropping a late packet on one path might affect the reliability of the whole block. Our results show that the parameters to minimize the PAoI lead to poor latency performance, and optimizing both at once might require significant resource overprovisioning.