Swift frameworks that use ObjC system libraries will still use objc_msgSend.
D'oh, right. A good test might be difficult. In the absence of that, I guess the safe bet is just to count every Swift binary as a false positive for ObjC, though that's not quite fair, since you can mix the two in the same code base.
Still, the test for Swift binaries seems accurate, and if you look at iOS 13.1 vs 14.0, for example, according to the chart there was an increase of 157 Swift binaries and 446 Objective-C binaries. If we assume there are 157 "false positives" in the ObjC binaries, that's still an increase of 289 ObjC binaries that don't use Swift at all.