Sign in with
Sign up | Sign in

Test Settings

Benchmarking Windows 7: Harder, Better, Faster, Stronger?

Modern hardware and software deserve each other, so we used some of our latest parts to gauge the performance difference of each operating system.

Test System Configuration
CPUIntel Core i7-870 (2.93 GHz, 8MB Cache)
CPU CoolerThermalright MUX-120
MotherboardAsus P7P55D, BIOS 0606 (09/03/2009), P55 Express Chipset, LGA 1156
RAMKingston KHX2133C9D3T1K2/4GX (4GB)
DDR3-2133 at DDR3-1600 CAS 8-8-8-24
GraphicsXFX GeForce GTX 285 XXX Edition
670 MHz GPU, GDDR3-2500
Hard DriveWestern Digital Velociraptor WD3000HLFS, 300GB, 10,000 RPM, SATA 3 Gb/s, 16MB cache
SoundIntegrated HD Audio
NetworkIntegrated Gigabit Networking
850W, ATX12V v2.2, EPS12V
New OSMicrosoft Windows 7 Ultimate x64
Legacy OSMicrosoft Windows Vista Ultimate x64 SP1
GraphicsNvidia GeForce 190.62 WHQL
ChipsetIntel INF

We used Asus’ P7P55D motherboard. Featuring Intel’s latest LGA 1156 socket and P55 Express PCH, the board took top honors, alongside one from Gigabyte, in our recent mainstream roundup. Better compatibility with this tester’s ancient drive-imaging software made Asus the default choice.

The reason for using so modern a motherboard is to support Intel’s latest LGA 1156 processors. Turbo Boost allows its Core i7-870 to increase CPU multipliers up to 27x (3.6 GHz), 26x (3.46 GHz), and 24x (3.2 GHz) for single-, dual-, and multi-threaded applications.

One significant fact about LGA 1156 processors is that they require high C-states (sleep states) for three cores in order to allow the highest multiplier to affect a single core. Rumors of better C-state function under Windows 7, if true, could give the new OS a significant performance advantage in single-threaded applications.

Thermalright’s new MUX-120 cooler brings Cogage True Spirit performance to LGA 1156 processors.

Benchmark Configuration
3D Games

Patch 1.2.1, DirectX 10, 64-bit executable, benchmark tool
Test Set 1: High Quality, No AA
Test Set 2: Very High Quality, 8x AA
Far Cry 2Patch 1.03, DirectX 10, in-game benchmark
Test Set 1: High Quality, No AA
Test Set 2: Ultra High Quality, 8x AA
S.T.A.L.K.E.R. Clear SkyClear Sky Benchmark version
Test Set 1: High Preset, DX10 EFDL, No AA
Test Set 2: Ultra Preset, DX10 EFDL, 4x MSAA
World in ConflictPatch 1009, DirectX 10, timedemo
Test 1: High Details, No AA / No AF
Test 2: Very High Details 4x AA / 16x AF
Audio/Video Encoding
Apple iTunesVersion: x64
Audio CD ("Terminator II" SE), 53 min
Default format AAC
Lame MP3Version: 3.98.2, wave to MP3
Audio CD "Terminator II" SE, 53 min
TMPEGEnc 4.0 ExpressVersion:
Import File: Terminator 2 SE DVD (5 Minutes)
Resolution: 720x576 (PAL) 16:9
DivX 6.8.5Encoding mode: Insane Quality
Enhanced multithreading enabled using SSE4
Quarter-pixel search
XviD 1.2.2Display encoding status = off
MainConcept Reference 1.6.1
Reference H.264 Plugin Pro 1.5.1
MPEG2 to MPEG2 (H.264), MainConcept H.264/AVC Codec, 28 sec HDTV 1920x1080 (MPEG2), Audio: MPEG2 (44.1 kHz, 2 Channel, 16-Bit, 224 kbp/s), Mode: PAL (25 FPS)
Adobe Photoshop CS4Version: 11.0 x64, Filter 15.7 MB TIF Image
Radial Blur, Shape Blur, Median, Polar Coordinates
Autodesk 3ds Max 2009Version: 11.0 x64, Rendering Dragon Image at 1920x1080 (HDTV)
Grisoft AVG Anti-Virus 8.5Version: 8.5.287, Virus base: 270.12.16/2094, Benchmark: Scan 334 MB Folder of ZIP/RAR compressed files
WinRAR 3.90Version x64 3.90, Dictionary = 4,096 KB, Benchmark: THG-Workload (334 MB)
WinZip 12Version 12.1, WinZip Command Line Version 3.0, Compression = Best, Benchmark: THG-Workload (334 MB)
Synthetic Benchmarks and Settings
PCMark VantageVersion: 1.00 x64, System, Memory, Hard Disk Drive benchmarks, Windows Media Player
SiSoftware Sandra 2009 SP4aVersion 2009.9.15.130, CPU Test = CPU Arithmetic / MultiMedia, Memory Test = Bandwidth Benchmark
BAPCo SYSmark 2007 PreviewVersion 1.05.958 Official Run (with conditioning run)
Display all 151 comments.
This thread is closed for comments
  • 0 Hide
    SpadeM , October 26, 2009 6:24 AM
    The article doesn't say much but I personaly would have preferred if you chose a 5850 or 5870 as the graphics card. Since you said
    Modern hardware and software deserve each other, so we used some of our latest parts to gauge the performance difference of each operating system.

    Who knows,maybe it would have made a difference in the numbers, in power consumption.
  • 3 Hide
    themadmanazn , October 26, 2009 6:28 AM
    Doesn't seem to be a huge difference from a performance point of view, but if it isn't as in your face as Vista, still a win =P
  • 2 Hide
    rivalneighbour , October 26, 2009 6:34 AM
    Thank you T.Soderstrom for this writeup.
  • -2 Hide
    jj463rd , October 26, 2009 6:36 AM
    One of my local television news Komo had a forum and some discussions about Windows 7 over Windows Vista.There were quite a few people who complained about running Vista on their PC.However most of the complainers (and there were a lot of them) had PC's with specifications that just barely met Vista's requirements.
    These people had outdated and obsolete hardware (probably owned lame OEM name brand PC's)no wonder that they had problems.Anyway thanks for the benchmarking of 7 vs Vista.The conclusion is rather interesting especially about a game running SMOOTHER and the feel of 7 being 7% to 10% faster than Vista.I like smoother gameplay.
  • 24 Hide
    Anonymous , October 26, 2009 6:40 AM
    Would have been nice to see Windows XP included as well. Just to know how much difference there really is in terms of performance between all 3 O/s's. From the above tests, there seems little reason to move to Win7 from Vista based on performance alone....
  • 9 Hide
    Rock_n_Rolla , October 26, 2009 6:59 AM
    What matters most is that Windows 7 gives way to what many are really
    after, A reliable and efficient Operating System as a replacement to their
    Windows XP, which millions and millions of people are still using.
    From the DX11 and Shader 5 hype, To Win XP mode to Fast Bootup to
    Increased FPS n gaming to strong security features... Well, Its up to
    them which versions is which. :) 
  • 7 Hide
    razor512 , October 26, 2009 7:10 AM
    waste of an article especially since they said "While most Tom’s Hardware readers initially resisted the switch from Windows XP"

    should have benchmarked it against windows xp (fresh install)

    while windows 7 is faster in some areas compared to windows vista, but it has lag spikes which causes CPU intensive tasks which lowers CPU benchmark results.
  • 1 Hide
    Crashman , October 26, 2009 7:17 AM
    Razor512waste of an article especially since they said "While most Tom’s Hardware readers initially resisted the switch from Windows XP"should have benchmarked it against windows xp (fresh install)while windows 7 is faster in some areas compared to windows vista, but it has lag spikes which causes CPU intensive tasks which lowers CPU benchmark results.

    The article also explains that XP x64 or Windows 7 x86 weren't options. What, you wanted 32-bit XP compared to 64-bit Vista and 7?
  • 8 Hide
    buwish , October 26, 2009 7:31 AM
    I think that as more apps are written specifically for W7, we'll see a vast improvement over these benchmarks. Just have to give it a bit of time.
  • 27 Hide
    megabuster , October 26, 2009 7:34 AM
    Why are we still testing W7 vs Vista SP1 when SP2 has been released for a while now?
  • 0 Hide
    liquidsnake718 , October 26, 2009 7:38 AM
    Thank you for finally putting an Nvidia GPU card up. Albeit it is the last and best version of the GTX285... the only other cards better than this is the GTX295 and all its vendors but its considered a x2 card.....

    I guess its official that the GTX2xx cards are basically dead.................
  • 15 Hide
    razor512 , October 26, 2009 7:41 AM
    CrashmanThe article also explains that XP x64 or Windows 7 x86 weren't options. What, you wanted 32-bit XP compared to 64-bit Vista and 7?

    they should have added both 32 bit windows xp and 64 bit (poor drivers and all)

    if 64 bit xp was really that unpopular then that means most people sticking with XP will be using the 32 bit version, so benchmark them show the users who stuck with XP what they will gain with going to windows 7

    I have the 64 bit version of windows 7 and 64 bit windows vista and 32 bit windows xp installed and compared to all of them windows xp is still the quickest. common things done in the OS especially the menu system and other parts of the OS require less hard drive activity to load, they load pretty much instantly while with vista theres a noticeable delay because it has to load up the eye candy along with the content, this gives the OS a sluggish feel.

    gaming benchmarks are lower but actual game play feels around the same since on both xp and windows 7 my frame rate in many games are pretty high that loosing a few FPS wont really be noticeable but it doesn't change the fact that it is slower

    so toms hardware, please show the windows XP users what they have to gain if they move to windows 7. comparing windows 7 to vista wont help anyone who decided to stick with windows xp

    thats like walking up to a group of people who decided to stick with their small cars instead of upgrading to a SUV and you trying to convince them to get a SUV by comparing the SUV to a M1A1D Abrams tank
    it doesn't show the small car owner what they are getting because the benchmark has nothing to do with them

    suppose you owned a company that makes makes the zune HD and I walked in to show your company a new mobile CPU for the zune HD but in my presentation I only mentioned how much better the new CPU performs compared to the stock CPU inside of a ipod touch
    (I bet security would be dragging me out of the room)
  • 6 Hide
    cough-fee , October 26, 2009 7:50 AM
    IMO, the results for Windows 7 are disappointing. If it can only beat Vista by "7% to 10%", then it must be far less with XP.
  • 2 Hide
    alterecho , October 26, 2009 7:53 AM
    i really do wish the reviewers include a mid end configuration for their
    reviews. thats where you'll see a lot of differnce since there is the
    factor of 'threshold' which plays a role.
  • 15 Hide
    barathn , October 26, 2009 8:02 AM
    Why there is no comparison with XP..

    While doing Benchmark, Test the relative configuration with Low end CPUs like mainstream CPUs, Average RAM etc, which puts the majority of mainstream users relate to the article..

  • 11 Hide
    Anonymous , October 26, 2009 8:02 AM
    Disappointing article. Ive been waiting for benchmarks....and you didnt show xp numbers. Bleh.

    So many users still on xp, some benchmarks to show what the difference is in moving to 7 is what is needed.


    with that said the vista vs 7 numbers are very disappointing. Seems they have made FAR less progress then the hype surrounding 7 would suggest. Im sure its better then vista, but who cares, vista sucks. Compare to xp and let us know where they are REALLY at.
  • -2 Hide
    Anonymous , October 26, 2009 8:14 AM
    i think microsoft is paying anandtech, tom'shardware and other well known pc review sites to give good reviews because if you really read the charts they show that win7 is worse than xp
  • -1 Hide
    arkadi , October 26, 2009 8:22 AM
    I had nothing but problems with Windows7, True it looks and feels nice, and i have it installed on my dell e4300 with no issues btw , but if you want stable reliable OS on some what complex setup, Windows7 just isn't ready. I had a lot unexplained problems on my main computer, problems with storage (thing that worked perfect with Vista, and a lot of stability issues, so i am still favor older VistaX64 sp1. As i see it, it all in publicity and how you promote your product, Microsoft did a good job with windows 7. Well you did see the numbers of windows 7. It superiority at this point is some what questionable, but every body like it...why?
  • 1 Hide
    programit , October 26, 2009 8:32 AM
    I am disappointed in this article as it feels like a Microsoft backed study/promo? Benchmarks appear slower but its really faster?
    I've been using Windows 7 since Beta and it IS slower than XP and Vista and it FEELS slower, and it loads slower,.. .. ..! This is on a X2 Laptop, core 2 intel and a Quad core Phenom II systems.
    As far as gaming goes theres really little to justify DirectX 10 or 11 at this stage so until software supports these so called advanced technologies then the benefit is minimal.
    I scored Windows 7 premium for minimal cost so I WILL run it at this stage but not because it better or faster. Because its there!
    My primary Quad core is back to Vista x64 (fastest and smoothest machine) and my laptop is back to XP (Smaller CPU but comparable to the Windows 7 machine in feel. - XP appears faster but is really slower - Slower CPU)
    Windows 7 will run on the Core 2 and it runs?
  • 12 Hide
    The-Darkening , October 26, 2009 8:46 AM
    I was hoping to see XP vs Vista vs 7. A 3-way bench.

    You couldn't do it here, but did it in the PSP vs DSi vs... Iphone????? comparison. Great!
Display more comments