Couple hours later, Hogan is faster than Handlebars: http://jsperf.com/t-bench2/7

I may be misunderstanding this, but that benchmark appears to be based on an in-browser compilation, while Hogan's advantage is the ability to precompile templates.

The compile happens in the setup of the benchmark. So the actual benchmark is testing the rendering speed of the compiled templates.

Handlebars is also capable of precompiling AFAIK.