Simon Crosby, CTO of XenSoure, recently posted on his Blog discussing the VMware Benchmark Performance paper comparing VMware ESX 3.0.1 and Xen 3.0.3.  In it, he writes:

Recently our friends at VMware published a performance comparison between ESX Server and the Xen™ hypervisor. In case the document disappears for some reason, I stashed away a spare copy, here.

The paper shows Xen 3.0.3 performing poorly in comparison with ESX Server 3.0.1 on a set of standard OS benchmarks run in a Windows Server 2003 R2 VM, including Netperf, Passmark, SPECCPU and SPECJBB. In almost every test the VMware build of Xen performed worse than ESX - indeed so badly that VMware concluded that Xen 3.0.3 is in no way ready for enterprise use. VMware also concludes that Intel VT, which Xen uses for hardware assisted virtualization of Windows, is a major contributor to Xen’s apparently shoddy performance.

To counter this, XenSource performed the same types of benchmarking on a very similar machine, using the commercial XenSource XenEnterprise product against VMware.  The current report does not show the VMware benchmark numbers because of the VMware EULA - Before you can publish VMware benchmark test numbers, you must get approval from VMware on your methodology, etc.  XenSource has requested this from VMware.  In the mean time, they supply the results against bare metal, and have place holders in there about VMware.

You can read Simon's entire post, here.  And you can grab the XenSource Benchmark paper without VMware numbers, here.