As it is mine.
Now you see why I do three to four (of a SF) at a time, simultaneously. I hate having to make multiple passes, much less trying to remember how one hit me (or having to do unfair comparisons at different maturation points).
I think you’re more likely to struggle, or get an incomplete impression by trying to do “flat batch tests” (IE: all tests at 2%). At least, that was my experience when I walked that path back when…
JMHO. YMMV.