Note that the difference in JavaScript test scores in that article is almost entirely due to differences on the V8 benchmark.

So more precisely, Chrome is fastest by a huge margin on the benchmark they explicitly tuned for.

You're welcome to pick pretty much any real world application, and I bet chrome will be ahead.

Also, Chrome is the fastest in V8 by a huge margin, while similar or a tiny bit slower in other benchmarks like Kraken or SunSpider

http://arewefastyet.com/

> You're welcome to pick pretty much any real world application, and I bet chrome will be ahead.

There are plenty of real-world JS applications where Chrome (well, V8) is much slower than competing browsers. Just browse through V8's bug tracker. For example, here is one I filed,

http://code.google.com/p/v8/issues/detail?id=1630

And I am sure there are even more such issues on the internal (non-public) issue trackers.

Different JS engines tune for different things, we can no longer say that any one of them is simply "faster" than all the rest. It depends on the benchmark.

The sunspider tests are also fairly dubious as a performance indicator because of their very short execution time, the Chrome team posted a modification which ran it 50 times to get a better idea of steady-state performance (http://blog.chromium.org/2011/05/updating-javascript-benchma...). Sunspider does act as a fairly good indicator of any latency overhead the JIT adds, though.

In terms of real-world scripting, almost any script I've benchmarked has always been ~1.5-2 times faster in Chrome than firefox (versions 4 through 6), except when bound by API calls (last I checked Firefox was on-par or better when dealing with TypedArrays). It looks like TypeInference might be a really big win though.

> You're welcome to pick pretty much any real world > application

The last one I tried was 5x slower in Chrome than in Firefox... Sadly, it's not a publicly available url.