Originally published on PrepStack. Cross-posting the TL;DR here.

We run a multi-tenant analytics SaaS on ASP.NET Core (~110k MAU, ~3,200 req/sec peak, ~95k LOC) and benchmarked .NET 9, .NET 10 (current LTS), and .NET 11 previews on the same harness and the same production workload — not synthetic microbenchmarks.

The numbers (9 -> 10, GA, near-zero code changes)

Metric

.NET 9