Few week ago I found comparison clickhouse vs other analytics DBs. So there was a mongo with a very bad times. I rewrote queries and add indexes to speed up (from ×3628.01 to ×444.53 current). But in some cases I can't got better results and even got worse (Q30 and Q31) with index usage. Count (Q0) didn't use index or use them in some strange way.
Bench repo: https://github.com/ClickHouse/ClickBench
Comparison site: https://benchmark.clickhouse.com/

So I think something going wrong on core side and could be reworked/optimized if so much time needed to make no so complex queries.
Other queries also need to be checked and extremely slow data loading too (more than 12 hours for 100m docs with 16 indexes)

I also tested timeseries collections but queries was even slower. U can check it anyway by creating TS collections instead of just importing data in benchmark script