Java's GCs are a generation ahead, though, in both throughput-oriented and latency-sensitive workloads [1]. Though Go's GC did/does get a few improvements and it is much better than it was a few years ago.

[1] ZGC has basically decoupled the heap size from the pause time, at that point you get longer pauses from the OS scheduler than from GC.

Do you have a source for this? My understanding is Go's GC is much better optimized for low latency.