Let's ignore your guesses about "most FP communities" and look at your example -

iirc Andy Fingerhut started benchmarking Clojure programs more than a year before Clojure was even included in the benchmarks game.

https://github.com/jafingerhut/clojure-benchmarks

Here's another thread "Comparing clojure speed to java speed" which has nothing what-so-ever to do with the benchmarks game -

http://groups.google.com/group/clojure/browse_thread/thread/...

(Incidentally, those "hotspot knobs" made the Clojure programs slightly slower but forced collection of the temporary objects that were showing up as much greater memory use than the Java programs.)