When he first posted it, it did, it looks like recent changes have brought that down:

https://github.com/fukamachi/woo/commit/be4a0db688af05ee204e...

Right. When I added default headers, the score went way down.

Probably libevent2 is the bottleneck and no way to make it faster without switching its backend (the cl-async's author is working on rewriting it with libuv now).

Out of curiosity did you try basic-binary-ipc? I would expect it would lose out to cl-async, but have never benchmarked the two against each other.

It would be quite surprising if it did, since Node's HTTP parser isn't Node/JavaScript, but highly optimized C.