Perhaps I wasn't explicit enough in the post, but yes I realize this. The point I was trying to make is that whatever the reason (including the purpose of the infrastructure, its usage patterns, its requirements), if a project could satisfy its purpose with fewer resources/less GDP needing to be reinvested over time, then this represents a higher relative return on their investment. GDP, having the dimension of time, wouldn't necessarily reflect their overall wealth, including the uncounted utility from historical investments.
The upfront investment of a Roman road might still be comparable to the lifetime investment of a modern one when you factor the human resource. How many man hours are spent on a mile of road, including building the tools (cement truck, bulldozer, etc) now versus the mass manual labor required then.
