The benchmark linked in the comments shows 7-38% improvements. Nothing to scoff at, but if you need PGBouncer that probably won't make enough of a difference.
It certainly isn't much of an improvement in connection latency (the connections are still pretty heavy), but it is a massive improvement in transaction throughput with higher numbers of connections. If you scroll down a bit, there is now higher TPS even at 5000 connections than previously could be had at 100 connections. That fixes a massive amount of pain that previously only could be solved with pgbouncer.
https://www.depesz.com/2020/08/25/waiting-for-postgresql-14-...