In their evaluation it appears they are comparing their server written in C or C++ (since they call OS functions like poll) to SEDA which is written in Java. In the original SEDA paper, if I remember correctly, the authors noted SEDA wasn't as fast as one of the servers written in C that they used for comparison reasons, but the authors were just trying to demonstrate a proof of concept of the architecture.

This doesn't seem like a particularly fair comparison of architectural ideas. A better one IMHO would have been to implement their server in Java or re implement SEDA in C.