Read the second link to see an audit of nVidia and ATi drivers. nVidia loses 24.1% and ATi loses 1.9% with the patch installed.

Quote:

Futuremark Headlines 3DMark03 Patch 330 Released Fri 2003-05-23 Saratoga, California USA – May 23rd, 2003 3DMark®03 incorporates many ground breaking new features and technologies and sets the standard for easily and objectively measuring and comparing modern PCs’ 3D graphics performance. Recently, there have been questions and some confusion regarding 3DMark®03 results obtained with certain NVIDIA drivers. We have now established that NVIDIA’s Detonator FX drivers contain certain detection mechanisms that cause an artificially high score when using 3DMark®03. We have just published a patch 330 for 3DMark03 that defeats the detection mechanisms in the drivers and provides correct results.

Download the 3DMark03 Patch 330 here:

http://www.futuremark.com/download/?...patch330.shtml

A detailed audit report of the drivers and 3DMark03 is available at:

http://www.futuremark.com/companyinf...dit_report.pdf

Here's another take on the nVidia driver issue as relates to 3DMark 03,by Zardon over at Driver Heaven. It's quite long.
Read it here.

And here is nVidia's response on the issue, also located at Driver Heaven.

And here's an "Official" reply from ATI. I couldn't verify it though.
Didn't find it at ATi's site, this came from nVnews.

Quote:

The 1.9% performance gain comes from optimization of the two DX9 shaders (water and sky) in Game Test 4 . We render the scene exactly as intended by Futuremark, in full-precision floating point. Our shaders are mathematically and functionally identical to Futuremark's and there are no visual artifacts; we simply shuffle instructions to take advantage of our architecture. These are exactly the sort of optimizations that work in games to improve frame rates without reducing image quality and as such, are a realistic approach to a benchmark intended to measure in-game performance. However, we recognize that these can be used by some people to call into question the legitimacy of benchmark results, and so we are removing them from our driver as soon as is physically possible. We expect them to be gone by the next release of CATALYST.