The performance gap between performing cache-hot lookups vs lookups that miss can be 10X. The increase is more a reflection of that rather than doing more operations.

The RAM model doesn't concern itself with memory hierarchies or slow ops (ie divisions are supposed to be as fast as additions.)

For example, if you were benchmarking cuckoo hashing lookups, the results would look similar even though the number of operations is deterministically O(1) rather than expected O(1).