We are a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for us to earn fees by linking to Amazon.com and affiliated sites.
[nextpage title=”Introduction”]
GeForce 7900 GTX is a very high-end graphics chip provided by NVIDIA. In fact, before the release of GeForce 7950 GX2, GeForce 7900 GTX was NVIDIA’s fastest graphics chip. In this review we will compare GeForce 7900 GTX to other products from both NVIDIA and ATI. Check it out.
Figure 1: NVIDIA GeForce 7900 GTX.
Our review is based on a reference model from NVIDIA. Video card manufacturers usually have two options for their products: follow the reference board from the chip manufacturer or design a board by themselves. Since the life cycle of video cards are very short these days, almost all manufacturers choose to simply follow the reference design, sometimes changing the cooler or overclocking the card. So by reviewing a reference model or a model based on it we will have an idea of the performance of almost all cards based on the same chip available on the market.
GeForce 7900 GTX runs at 650 MHz and accesses its video memory at 1.6 GHz. Like all high-end GPUs it accesses its video memory using a 256-bit interface. All GPUs on NVIDIA GeForce 7900 family has 24 pixel shader units, so the main difference between the current three members of GeForce 7900 family is the clock used. GeForce 7950 GX2, however, has two GeForce 7950 GPUs, so everything on this video card is doubled.
You can see in our tutorial “NVIDIA Chips Comparison Table” the difference between GeForce 7900 GTX and other chips from NVIDIA, while on our tutorial “ATI Chips Comparison Table” you can compare it to its competitors from ATI.
On Figures 2 and 3 you can see the GeForce 7900 GTX reference model from NVIDIA.
Figure 2: NVIDIA GeForce 7900 GTX.
Figure 3: NVIDIA GeForce 7900 GTX, back view.
[nextpage title=”GeForce 7900 GTX Reference Model from NVIDIA”]
GeForce 7900 GTX reference model uses a huge cooler, as you have seen on the previous pictures. By using a big fan the video card is able to produce less noise, since it can rotate at a lower speed to achieve the same performance of a smaller fan.
We removed the video card cooler to take a look. It has an aluminum body with a copper base, using four heat-pipes to connect its base to its aluminum fins. As you can notice by looking at Figures 4 and 5 the heatsink touches the memory chips, cooling them down.
Figure 4: GeForce 7900 GTX reference model heatsink.
Figure 5: GeForce 7900 GTX reference model heatsink.
In Figure 6, you can see the reviewed video card without its cooler.
Figure 6: GeForce 7900 GTX reference model without its cooler.
This video card uses eight GDDR3 512-Mbit 1.1 ns chips from Samsung (K4J52324QC-BJ11), making its 512 MB video memory (512 Mbits x 8 = 512 MB). These chips can run up to 1.8 GHz. Since this video card accesses its memory at 1.6 GHz, there is 12.5% headroom if you wish to overclock it inside its specs.
In Figure 7, you can see GeForce 7900 GTX chip. As you can see, it is internally called G71-U by NVIDIA.
Figure 7: GeForce 7900 GTX chip.
[nextpage title=”Main Specifications”]
- Graphics chip: GeForce 7900 GTX.
- Memory: 1.1 ns 256-bit 512 MB GDDR3 memory from Samsung (K4J52324QC-BJ11), running at 1.6 GHz (800 MHz DDR).
- Bus type: PCI Express x16.
- Connectors: Two DVI and one mini-DIN for S-Video and Component Video output.
- Number of CDs/DVDs that come with this board: N/A.
- Games that come with this board: N/A.
- Programs that come with this board: N/A.
- More information: https://www.nvidia.com
- Average price in the US*: USD 500.00
* Researched at Shopping.com on the day we published this review.
[nextpage title=”How We Tested”]
During our benchmarking sessions, we used the configuration listed below. Between our benchmarking sessions the only variable was the video card being tested.
Hardware Configuration
- Motherboard: DFI LAN Party 925X-T2 (Intel 925X, Sep. 20th, 2004 BIOS)
- CPU: Pentium 4 3.4 GHz LGA 775
- Memory: Two 512 MB DDR2-533 CM2X512-4200 CL4 from Corsair memory modules
- Hard Drive: Maxtor DiamondMax 9 Plus (40 GB, ATA-133)
- Screen resolution: [email protected] Hz
Software Configuration
- Windows XP Professional installed using NTFS
- Service Pack 2
- Direct X 9.0c
- Intel inf driver version: 6.0.1.1002
- ATI video driver version: 4.10 (6.14.10.6483)
- ATI video driver version: 4.12 (Radeon X850 Platinum Edition)
- ATI video driver version: 5.3 (Radeon X800 GT)
- ATI video driver version: 5.9 (Radeon X800 GTO)
- ATI video driver version: 6.1 (Radeon X1600 XT from HIS)
- ATI video driver version: 8.173 beta (Radeon X1000 series)
- ATI video driver version: 8.203.3.0 (Radeon X1900 XTX)
- NVIDIA video driver version: 66.93
- NVIDIA video driver version: 77.72 (GeForce 7800 GTX)
- NVIDIA video driver version: 78.02 (GeForce 7800 GT)
- NVIDIA video driver version: 81.98 (GeForce 6800 GS)
- NVIDIA video driver version: 84.21 (GeForce 7600 and 7900 series)
- NVIDIA video driver version: 91.29 (GeForce 7950 GX2)
Used Software
We adopted a 3% error margin; thus, differences below 3% cannot be considered relevant. In other words, products with a performance difference below 3% should be considered as having similar performance.
[nextpage title=”3DMark2001 SE”]
3DMark2001 SE measures video card performance simulating DirectX 8.1 games. It is very effective software for evaluating the performance from previous-generation games, programmed using DirectX 8. In this software we run six tests. We run the software in three resolutions, 1024x768x32, 1280x1024x32 and 1600x1200x32, first without antialising and with no frame buffer, then we put the antialising at 4 samples and the frame buffer at triple-buffering. This improves the video quality but lowers the performance. We were willing to see how much performance we lost by putting the VGA to run at the maximum possible image quality. It is important to note that ATI chips can run at 6x antialising. Since NVIDIA chips cannot run at this configuration, we had to use 4x antialising to use a configuration that is valid to all video cards included in our bechmarks, allowing direct comparison between them.
You may be asking yourself why we added an old program in a review of a latest generation video card. To us, it is as important to know the performance of a video card with the latest games as it is to know its performance in an older game. That’s why we kept this software in our methodology.
The results you check below. Keep in mind that models marked as “OC” are factory-overclocked. GeForce 7900 GT OC from XFX was running at 550 MHz with its memory being accessed at 1.63 GHz (815 MHz DDR) while the standard clock configuration for a GeForce 7900 GT is 450 MHz/1.32 GHz (660 MHz DDR). GeForce 7950 GX2 OC from XFX was running at 570 MHz with its memory being accessed at 1.55 GHz (775 MHz DDR) while the standard clock configuration for a GeForce 7950 GX2 is 500 MHz/1.2 GHz (600 MHz DDR).
| 3DMark2001 SE – 1024×768 | Score | Difference |
| Radeon X850 XT P.E. (ATI) | 23,004 | 1.25% |
| GeForce 7950 GX2 (NVIDIA) | 22,967 | 1.09% |
| Radeon X1800 XT (ATI) | 22,731 | 0.05% |
| GeForce 7900 GTX (NVIDIA) | 22,720 | |
| GeForce 7900 GT OC (XFX) | 22,347 | 1.67% |
| GeForce 7950 GX2 OC (XFX) | 22,228 | 2.21% |
| GeForce 7800 GTX (MSI) | 21,858 | 3.94% |
| GeForce 7900 GT (NVIDIA) | 21,510 | 5.63% |
| Radeon X1800 XL (ATI) | 21,487 | 5.74% |
| Radeon X1900 GT (Connect3D) | 21,433 | 6.00% |
| GeForce 7800 GT (NVIDIA) | 21,043 | 7.97% |
| Radeon X800 GT (HIS) | 20,299 | 11.93% |
| GeForce 6800 GS (NVIDIA) | 20,084 | 13.12% |
| GeForce 6800 GT (NVIDIA) | 20,072 | 13.19% |
| Radeon X1600 XT (ATI) | 19,865 | 14.37% |
| GeForce 7600 GT (NVIDIA) | 19,864 | 14.38% |
| Radeon X800 GTO (HIS) | 19,797 | 14.76% |
| Radeon X700 Pro (Sapphire) | 18,630 | 21.95% |
| GeForce 6600 GT (XFX) | 17,881 | 27.06% |
| Radeon X1900 XTX (ATI) | 17,412 | 30.48% |
| GeForce 7600 GS (NVIDIA) | 16,840 | 34.92% |
| Radeon X600 XT (ATI) | 14,453 | 57.20% |
| GeForce 6600 (Albatron) | 14,132 | 60.77% |
| Radeon X600 Pro (Sapphire) | 12,545 | 81.11% |
| 3DMark2001 SE – 1280×1024 | Score | Difference |
| GeForce 7950 GX2 OC (XFX) | 21,466 | 2.80% |
| GeForce 7950 GX2 (NVIDIA) | 21,449 | 2.72% |
| Radeon X1800 XT (ATI) | 21,038 | 0.75% |
| GeForce 7900 GTX (NVIDIA) | 20,882 | |
| Radeon X850 XT P.E. (ATI) | 20,868 | 0.07% |
| GeForce 7900 GT OC (XFX) | 20,647 | 1.14% |
| GeForce 7800 GTX (MSI) | 20,096 | 3.91% |
| GeForce 7900 GT (NVIDIA) | 19,924 | 4.81% |
| Radeon X1800 XL (ATI) | 19,768 | 5.64% |
| Radeon X1900 GT (Connect3D) | 19,755 | 5.70% |
| GeForce 7800 GT (NVIDIA) | 19,465 | 7.28% |
| GeForce 6800 GT (NVIDIA) | 18,436 | 13.27% |
| GeForce 6800 GS (NVIDIA) | 18,307 | 14.07% |
| GeForce 7600 GT (NVIDIA) | 18,228 | 14.56% |
| Radeon X800 GT (HIS) | 18,084 | 15.47% |
| Radeon X800 GTO (HIS) | 17,658 | 18.26% |
| Radeon X1600 XT (ATI) | 17,005 | 22.80% |
| Radeon X1900 XTX (ATI) | 16,750 | 24.67% |
| Radeon X700 Pro (Sapphire) | 15,721 | 32.83% |
| GeForce 6600 GT (XFX) | 15,464 | 35.04% |
| GeForce 7600 GS (NVIDIA) | 14,854 | 40.58% |
| GeForce 6600 (Albatron) | 11,403 | 83.13% |
| Radeon X600 XT (ATI) | 11,274 | 85.22% |
| Radeon X600 Pro (Sapphire) | 9,472 | 120.46% |
| 3DMark2001 SE – 1600×1200 | Score | Difference |
| GeForce 7950 GX2 OC (XFX) | 20,590 | 3.63% |
| GeForce 7950 GX2 (NVIDIA) | 20,369 | 2.52% |
| Radeon X1800 XT (ATI) | 19,986 | 0.59% |
| GeForce 7900 GTX (NVIDIA) | 19,868 | |
| GeForce 7900 GT OC (XFX) | 19,570 | 1.52% |
| Radeon X850 XT P.E. (ATI) | 19,382 | 2.51% |
| GeForce 7800 GTX (MSI) | 18,988 | 4.63% |
| GeForce 7900 GT (NVIDIA) | 18,793 | 5.72% |
| Radeon X1900 GT (Connect3D) | 18,749 | 5.97% |
| Radeon X1800 XL (ATI) | 18,390 | 8.04% |
| GeForce 7800 GT (NVIDIA) | 18,140 | 9.53% |
| GeForce 6800 GT (NVIDIA) | 16,784 | 18.37% |
| GeForce 7600 GT (NVIDIA) | 16,649 | 19.33% |
| GeForce 6800 GS (NVIDIA) | 16,590 | 19.76% |
| Radeon X1900 XTX (ATI) | 16,483 | 20.54% |
| Radeon X800 GTO (HIS) | 15,524 | 27.98% |
| Radeon X800 GT (HIS) | 15,498 | 28.20% |
| Radeon X1600 XT (ATI) | 14,481 | 37.20% |
| GeForce 6600 GT (XFX) | 13,694 | 45.09% |
| GeForce 7600 GS (NVIDIA) | 12,938 | 53.56% |
| Radeon X700 Pro (Sapphire) | 12,741 | 55.94% |
| GeForce 6600 (Albatron) | 9,059 | 119.32% |
| Radeon X600 XT (ATI) | 8,129 | 144.41% |
| Radeon X600 Pro (Sapphire) | 6,729 | 195.26% |
| 3DMark2001 SE – 1024×768 AAx4, FBx3 | Score | Difference |
| GeForce 7950 GX2 OC (XFX) | 21,165 | 3.49% |
| GeForce 7950 GX2 (NVIDIA) | 21,028 | 2.82% |
| Radeon X1800 XT (ATI) | 20,783 | 1.62% |
| GeForce 7900 GTX (NVIDIA) | 20,451 | |
| Radeon X850 XT P.E. (ATI) | 20,403 | 0.24% |
| GeForce 7900 GT OC (XFX) | 20,145 | 1.52% |
| Radeon X1800 XL (ATI) | 19,671 | 3.97% |
| Radeon X1900 GT (Connect3D) | 19,321 | 5.85% |
| GeForce 7800 GTX (MSI) | 19,208 | 6.47% |
| GeForce 7900 GT (NVIDIA) | 19,103 | 7.06% |
| GeForce 7800 GT (NVIDIA) | 18,336 | 11.53% |
| GeForce 6800 GT (NVIDIA) | 17,187 | 18.99% |
| Radeon X1900 XTX (ATI) | 16,979 | 20.45% |
| GeForce 6800 GS (NVIDIA) | 16,856 | 21.33% |
| Radeon X1600 XT (ATI) | 16,834 | 21.49% |
| GeForce 7600 GT (NVIDIA) | 16,775 | 21.91% |
| Radeon X800 GTO (HIS) | 16,529 | 23.73% |
| Radeon X800 GT (HIS) | 16,408 | 24.64% |
| Radeon X700 Pro (Sapphire) | 15,745 | 29.89% |
| GeForce 7600 GS (NVIDIA) | 15,021 | 36.15% |
| GeForce 6600 GT (XFX) | 13,635 | 49.99% |
| Radeon X600 XT (ATI) | 9,718 | 110.44% |
| GeForce 6600 (Albatron) | 8,928 | 129.07% |
| Radeon X600 Pro (Sapphire) | 8,210 | 149.10% |
| 3DMark2001 SE – 1280×1024 AAx4, FBx3 | Score | Difference |
| GeForce 7950 GX2 OC (XFX) | 19,774 | 5.30% |
| GeForce 7950 GX2 (NVIDIA) | 19,440 | 3.53% |
| Radeon X1800 XT (ATI) | 19,354 | 3.07% |
| GeForce 7900 GTX (NVIDIA) | 18,778 | |
| Radeon X850 XT P.E. (ATI) | 18,447 | 1.79% |
| GeForce 7900 GT OC (XFX) | 18,366 | 2.24% |
| Radeon X1800 XL (ATI) | 18,029 | 4.15% |
| Radeon X1900 GT (Connect3D) | 17,682 | 6.20% |
| GeForce 7900 GT (NVIDIA) | 17,142 | 9.54% |
| GeForce 7800 GTX (MSI) | 17,120 | 9.68% |
| GeForce 7800 GT (NVIDIA) | 16,302 | 15.19% |
| Radeon X1900 XTX (ATI) | 16,056 | 16.95% |
| GeForce 6800 GT (NVIDIA) | 15,117 | 24.22% |
| GeForce 6800 GS (NVIDIA) | 15,080 | 24.52% |
| GeForce 7600 GT (NVIDIA) | 14,294 | 31.37% |
| Radeon X1600 XT (ATI) | 13,833 | 35.75% |
| Radeon X800 GT (HIS) | 13,655 | 37.52% |
| Radeon X800 GTO (HIS) | 13,652 | 37.55% |
| GeForce 7600 GS (NVIDIA) | 12,892 | 45.66% |
| Radeon X700 Pro (Sapphire) | 12,364 | 51.88% |
| GeForce 6600 GT (XFX) | 10,487 | 79.06% |
| Radeon X600 XT (ATI) | 6,915 | 171.55% |
| GeForce 6600 (Albatron) | 6,049 | 210.43% |
| Radeon X600 Pro (Sapphire) | 5,755 | 226.29% |
| 3DMark2001 SE – 1600×1200 AAx4, FBx3 | Score | Difference |
| GeForce 7950 GX2 OC (XFX) | 18,772 | 8.37% |
| GeForce 7950 GX2 (NVIDIA) | 18,424 | 6.36% |
| Radeon X1800 XT (ATI) | 18,090 | 4.43% |
| GeForce 7900 GTX (NVIDIA) | 17,322 | |
| GeForce 7900 GT OC (XFX) | 16,919 | 2.38% |
| Radeon X850 XT P.E. (ATI) | 16,299 | 6.28% |
| Radeon X1800 XL (ATI) | 16,213 | 6.84% |
| Radeon X1900 GT (Connect3D) | 15,920 | 8.81% |
| Radeon X1900 XTX (ATI) | 15,734 | 10.09% |
| GeForce 7900 GT (NVIDIA) | 15,503 | 11.73% |
| GeForce 7800 GTX (MSI) | 15,362 | 12.76% |
| GeForce 7800 GT (NVIDIA) | 14,418 | 20.14% |
| GeForce 6800 GT (NVIDIA) | 11,829 | 46.44% |
| GeForce 6800 GS (NVIDIA) | 11,663 | 48.52% |
| Radeon X800 GTO (HIS) | 11,127 | 55.68% |
| Radeon X800 GT (HIS) | 10,659 | 62.51% |
| GeForce 7600 GT (NVIDIA) | 9,891 | 75.13% |
| Radeon X700 Pro (Sapphire) | 9,455 | 83.20% |
| Radeon X1600 XT (ATI) | 8,429 | 105.50% |
| GeForce 6600 GT (XFX) | 6,620 | 161.66% |
| GeForce 7600 GS (NVIDIA) | 5,625 | 207.95% |
| GeForce 6600 (Albatron) | 3,558 | 386.85% |
| Radeon X600 XT (ATI) | 3,205 | 440.47% |
| Radeon X600 Pro (Sapphire) | 2,606 | 564.70% |
[nextpage title=”3DMark03″]
3DMark03 measures performance by simulating games written to DirectX 9, which are contemporary games. We run this program in three resolutions, 1024x768x32, 1280x1024x32 and 1600x1200x32, first without antialising and anisotropic filtering, and then configuring antialising at 4x and anisotropic filtering also at 4x. This improves the video quality but lowers the performance. We were willing to see how much performance we lost by putting the VGA to run at the maximum possible image quality. It is important to note that ATI chips can run at 6x antialising. Since NVIDIA chips cannot run at this configuration, we had to use 4x antialising to use a configuration that is valid to all video cards included in our bechmarks, allowing direct comparison between them.
The results you check below. Keep in mind that models marked as “OC” are factory-overclocked. GeForce 7900 GT OC from XFX was running at 550 MHz with its memory being accessed at 1.63 GHz (815 MHz DDR) while the standard clock configuration for a GeForce 7900 GT is 450 MHz/1.32 GHz (660 MHz DDR). GeForce 7950 GX2 OC from XFX was running at 570 MHz with its memory being accessed at 1.55 GHz (775 MHz DDR) while the standard clock configuration for a GeForce 7950 GX2 is 500 MHz/1.2 GHz (600 MHz DDR).
| 3DMark03 – 1024×768 | Score | Difference |
| GeForce 7950 GX2 OC (XFX) | 26,189 | 41.83% |
| GeForce 7950 GX2 (NVIDIA) | 24,670 | 33.60% |
| GeForce 7900 GTX (NVIDIA) | 18,465 | |
| GeForce 7900 GT OC (XFX) | 17,261 | 6.98% |
| Radeon X1900 XTX (ATI) | 16,544 | 11.61% |
| Radeon X1800 XT (ATI) | 15,631 | 18.13% |
| GeForce 7900 GT (NVIDIA) | 15,375 | 20.10% |
| GeForce 7800 GTX (MSI) | 15,004 | 23.07% |
| GeForce 7800 GT (NVIDIA) | 13,760 | 34.19% |
| Radeon X1900 GT (Connect3D) | 13,630 | 35.47% |
| Radeon X1800 XL (ATI) | 13,144 | 40.48% |
| Radeon X850 XT P.E. (ATI) | 12,782 | 44.46% |
| GeForce 7600 GT (NVIDIA) | 12,111 | 52.46% |
| GeForce 6800 GS (NVIDIA) | 11,285 | 63.62% |
| GeForce 6800 GT (NVIDIA) | 11,223 | 64.53% |
| Radeon X800 GTO (HIS) | 9,563 | 93.09% |
| Radeon X1600 XT (ATI) | 9,352 | 97.44% |
| Radeon X800 GT (HIS) | 9,134 | 102.16% |
| GeForce 7600 GS (NVIDIA) | 8,213 | 124.83% |
| GeForce 6600 GT (XFX) | 8,056 | 129.21% |
| Radeon X700 Pro (Sapphire) | 7,295 | 153.12% |
| GeForce 6600 (Albatron) | 4,847 | 280.96% |
| Radeon X600 XT (ATI) | 4,128 | 347.31% |
| Radeon X600 Pro (Sapphire) | 3,468 | 432.44% |
| 3DMark03 – 1280×1024 | Score | Difference |
| GeForce 7950 GX2 OC (XFX) | 22,880 | 48.63% |
| GeForce 7950 GX2 (NVIDIA) | 21,038 | 36.66% |
| GeForce 7900 GTX (NVIDIA) | 15,394 | |
| GeForce 7900 GT OC (XFX) | 14,324 | 7.47% |
| Radeon X1900 XTX (ATI) | 13,888 | 10.84% |
| Radeon X1800 XT (ATI) | 13,045 | 18.01% |
| GeForce 7900 GT (NVIDIA) | 12,578 | 22.39% |
| GeForce 7800 GTX (MSI) | 12,239 | 25.78% |
| Radeon X1900 GT (Connect3D) | 11,119 | 38.45% |
| GeForce 7800 GT (NVIDIA) | 10,997 | 39.98% |
| Radeon X1800 XL (ATI) | 10,671 | 44.26% |
| Radeon X850 XT P.E. (ATI) | 10,314 | 49.25% |
| GeForce 7600 GT (NVIDIA) | 9,529 | 61.55% |
| GeForce 6800 GT (NVIDIA) | 8,836 | 74.22% |
| GeForce 6800 GS (NVIDIA) | 8,784 | 75.25% |
| Radeon X800 GTO (HIS) | 7,472 | 106.02% |
| Radeon X800 GT (HIS) | 7,039 | 118.70% |
| Radeon X1600 XT (ATI) | 6,943 | 121.72% |
| GeForce 7600 GS (NVIDIA) | 6,277 | 145.24% |
| GeForce 6600 GT (XFX) | 6,041 | 154.83% |
| Radeon X700 Pro (Sapphire) | 5,351 | 187.68% |
| GeForce 6600 (Albatron) | 3,538 | 335.10% |
| Radeon X600 XT (ATI) | 2,990 | 414.85% |
| Radeon X600 Pro (Sapphire) | 2,507 | 514.04% |
| 3DMark03 – 1600×1200 | Score | Difference |
| GeForce 7950 GX2 OC (XFX) | 21,176 | 50.29% |
| GeForce 7950 GX2 (NVIDIA) | 18,152 | 28.83% |
| GeForce 7900 GTX (NVIDIA) | 14,090 | |
| GeForce 7900 GT OC (XFX) | 12,060 | 16.83% |
| Radeon X1900 XTX (ATI) | 11,680 | 20.63% |
| Radeon X1800 XT (ATI) | 10,751 | 31.06% |
| GeForce 7900 GT (NVIDIA) | 10,445 | 34.90% |
| GeForce 7800 GTX (MSI) | 10,127 | 39.13% |
| GeForce 7800 GT (NVIDIA) | 9,822 | 43.45% |
| Radeon X1900 GT (Connect3D) | 9,100 | 54.84% |
| Radeon X1800 XL (ATI) | 8,743 | 61.16% |
| Radeon X850 XT P.E. (ATI) | 8,411 | 67.52% |
| GeForce 7600 GT (NVIDIA) | 7,701 | 82.96% |
| GeForce 6800 GT (NVIDIA) | 7,144 | 97.23% |
| GeForce 6800 GS (NVIDIA) | 7,035 | 100.28% |
| Radeon X800 GTO (HIS) | 5,940 | 137.21% |
| Radeon X1600 XT (ATI) | 5,295 | 166.10% |
| Radeon X800 GT (HIS) | 5,220 | 169.92% |
| GeForce 7600 GS (NVIDIA) | 4,930 | 185.80% |
| GeForce 6600 GT (XFX) | 4,640 | 203.66% |
| Radeon X700 Pro (Sapphire) | 3,938 | 257.80% |
| GeForce 6600 (Albatron) | 2,678 | 426.14% |
| Radeon X600 XT (ATI) | 2,131 | 561.19% |
| Radeon X600 Pro (Sapphire) | 1,797 | 684.08% |
| 3DMark03 – 1024×768 AAx4, Anisox4 | Score | Difference |
| GeForce 7950 GX2 OC (XFX) | 19,582 | 55.91% |
| GeForce 7950 GX2 (NVIDIA) | 17,431 | 38.78% |
| GeForce 7900 GTX (NVIDIA) | 12,560 | |
| GeForce 7900 GT OC (XFX) | 11,819 | 6.27% |
| Radeon X1900 XTX (ATI) | 11,576 | 8.50% |
| Radeon X1800 XT (ATI) | 10,989 | 14.30% |
| GeForce 7900 GT (NVIDIA) | 10,275 | 22.24% |
| GeForce 7800 GTX (MSI) | 9,929 | 26.50% |
| Radeon X1800 XL (ATI) | 9,325 | 34.69% |
| GeForce 7800 GT (NVIDIA) | 8,999 | 39.57% |
| Radeon X1900 GT (Connect3D) | 8,834 | 42.18% |
| Radeon X850 XT P.E. (ATI) | 8,108 | 54.91% |
| GeForce 7600 GT (NVIDIA) | 7,330 | 71.35% |
| GeForce 6800 GT (NVIDIA) | 6,919 | 81.53% |
| GeForce 6800 GS (NVIDIA) | 6,841 | 83.60% |
| Radeon X800 GTO (HIS) | 5,437 | 131.01% |
| Radeon X1600 XT (ATI) | 4,978 | 152.31% |
| Radeon X800 GT (HIS) | 4,693 | 167.63% |
| GeForce 7600 GS (NVIDIA) | 4,405 | 185.13% |
| GeForce 6600 GT (XFX) | 4,177 | 200.69% |
| Radeon X700 Pro (Sapphire) | 3,411 | 268.22% |
| GeForce 6600 (Albatron) | 2,378 | 428.17% |
| Radeon X600 XT (ATI) | 1,966 | 538.86% |
| Radeon X600 Pro (Sapphire) | 1,674 | 650.30% |
| 3DMark03 – 1280×1024 AAx4, Anisox4 | Score | Difference |
| GeForce 7950 GX2 OC (XFX) | 16,062 | 60.67% |
| GeForce 7950 GX2 (NVIDIA) | 14,067 | 40.71% |
| GeForce 7900 GTX (NVIDIA) | 9,997 | |
| Radeon X1900 XTX (ATI) | 9,467 | 5.60% |
| GeForce 7900 GT OC (XFX) | 9,368 | 6.71% |
| Radeon X1800 XT (ATI) | 9,050 | 10.46% |
| GeForce 7900 GT (NVIDIA) | 7,980 | 25.28% |
| GeForce 7800 GTX (MSI) | 7,733 | 29.28% |
| Radeon X1800 XL (ATI) | 7,249 | 37.91% |
| Radeon X1900 GT (Connect3D) | 6,979 | 43.24% |
| GeForce 7800 GT (NVIDIA) | 6,841 | 46.13% |
| Radeon X850 XT P.E. (ATI) | 6,278 | 59.24% |
| GeForce 7600 GT (NVIDIA) | 5,324 | 87.77% |
| GeForce 6800 GT (NVIDIA) | 5,172 | 93.29% |
| GeForce 6800 GS (NVIDIA) | 5,025 | 98.95% |
| Radeon X800 GTO (HIS) | 3,962 | 152.32% |
| Radeon X1600 XT (ATI) | 3,747 | 166.80% |
| Radeon X800 GT (HIS) | 3,475 | 187.68% |
| GeForce 7600 GS (NVIDIA) | 3,116 | 220.83% |
| GeForce 6600 GT (XFX) | 2,547 | 292.50% |
| Radeon X700 Pro (Sapphire) | 2,454 | 307.38% |
| GeForce 6600 (Albatron) | 1,497 | 567.80% |
| Radeon X600 XT (ATI) | 1,351 | 639.97% |
| Radeon X600 Pro (Sapphire) | 1,212 | 724.83% |
| 3DMark03 – 1600×1200 AAx4, Anisox4 | Score | Difference |
| GeForce 7950 GX2 OC (XFX) | 13,355 | 63.50% |
| GeForce 7950 GX2 (NVIDIA) | 11,629 | 42.37% |
| GeForce 7900 GTX (NVIDIA) | 8,168 | |
| Radeon X1900 XTX (ATI) | 7,852 | 4.02% |
| GeForce 7900 GT OC (XFX) | 7,563 | 8.00% |
| Radeon X1800 XT (ATI) | 7,364 | 10.92% |
| GeForce 7900 GT (NVIDIA) | 6,317 | 29.30% |
| GeForce 7800 GTX (MSI) | 6,148 | 32.86% |
| GeForce 7800 GT (NVIDIA) | 5,873 | 39.08% |
| Radeon X1800 XL (ATI) | 5,807 | 40.66% |
| Radeon X1900 GT (Connect3D) | 5,614 | 45.49% |
| Radeon X850 XT P.E. (ATI) | 5,024 | 62.58% |
| GeForce 7600 GT (NVIDIA) | 4,530 | 80.31% |
| GeForce 6800 GT (NVIDIA) | 4,018 | 103.29% |
| GeForce 6800 GS (NVIDIA) | 3,861 | 111.55% |
| Radeon X800 GTO (HIS) | 3,091 | 164.25% |
| Radeon X1600 XT (ATI) | 2,656 | 207.53% |
| Radeon X800 GT (HIS) | 2,563 | 218.69% |
| GeForce 7600 GS (NVIDIA) | 2,377 | 243.63% |
| Radeon X700 Pro (Sapphire) | 1,805 | 352.52% |
| GeForce 6600 GT (XFX) | 1,717 | 375.71% |
| GeForce 6600 (Albatron) | 1,027 | 695.33% |
| Radeon X600 XT (ATI) | 732 | 1015.85% |
| Radeon X600 Pro (Sapphire) | 684 | 1094.15% |
[nextpage title=”3DMark05″]
3DMark05 measures performance by simulating DirectX 9.0c games, i.e., using the new Shader 3.0 model. This programming model is used by Far Cry game and other games to be launched in the future. This new programming model is used by GeForce 6 and 7 series from NVIDIA and Radeon X1000 series from ATI.
We run this program in three resolutions, 1024x768x32, 1280x1024x32 and 1600x1200x32, first without antialising and anisotropic filtering, and then configuring antialising at 4x and anisotropic filtering also at 4x. This improves the video quality but lowers the performance. We were willing to see how much performance we lost by putting the VGA to run at the maximum possible image quality. It is important to note that ATI chips can run at 6x antialising. Since NVIDIA chips cannot run at this configuration, we had to use 4x antialising to use a configuration that is valid to all video cards included in our benchmark, allowing direct comparison between them.
The results you check below. Keep in mind that models marked as “OC” are factory-overclocked. GeForce 7900 GT OC from XFX was running at 550 MHz with its memory being accessed at 1.63 GHz (815 MHz DDR) while the standard clock configuration for a GeForce 7900 GT is 450 MHz/1.32 GHz (660 MHz DDR). GeForce 7950 GX2 OC from XFX was running at 570 MHz with its memory being accessed at 1.55 GHz (775 MHz DDR) while the standard clock configuration for a GeForce 7950 GX2 is 500 MHz/1.2 GHz (600 MHz DDR).
| 3DMark05 – 1024×768 | Score | Difference |
| GeForce 7950 GX2 OC (XFX) | 8,172 | 10.88% |
| GeForce 7950 GX2 (NVIDIA) | 8,096 | 9.85% |
| GeForce 7900 GTX (NVIDIA) | 7,370 | |
| Radeon X1900 GT (Connect3D) | 7,342 | 0.38% |
| Radeon X1800 XT (ATI) | 7,222 | 2.05% |
| GeForce 7900 GT OC (XFX) | 7,220 | 2.08% |
| Radeon X1900 XTX (ATI) | 6,982 | 5.56% |
| GeForce 7900 GT (NVIDIA) | 6,863 | 7.39% |
| GeForce 7800 GTX (MSI) | 6,789 | 8.56% |
| Radeon X1800 XL (ATI) | 6,471 | 13.89% |
| GeForce 7800 GT (NVIDIA) | 6,343 | 16.19% |
| Radeon X850 XT P.E. (ATI) | 5,732 | 28.58% |
| GeForce 7600 GT (NVIDIA) | 5,594 | 31.75% |
| Radeon X1600 XT (ATI) | 4,991 | 47.67% |
| GeForce 6800 GS (NVIDIA) | 4,941 | 49.16% |
| GeForce 6800 GT (NVIDIA) | 4,537 | 62.44% |
| Radeon X800 GTO (HIS) | 4,301 | 71.36% |
| Radeon X800 GT (HIS) | 3,993 | 84.57% |
| GeForce 7600 GS (NVIDIA) | 3,675 | 100.54% |
| Radeon X700 Pro (Sapphire) | 2,886 | 155.37% |
| GeForce 6600 GT (XFX) | 2,872 | 156.62% |
| GeForce 6600 (Albatron) | 1,701 | 333.27% |
| Radeon X600 XT (ATI) | 1,433 | 414.31% |
| Radeon X600 Pro (Sapphire) | 1,365 | 439.93% |
| 3DMark05 – 1280×1024 | Score | Difference |
| GeForce 7950 GX2 OC (XFX) | 7,918 | 13.73% |
| GeForce 7950 GX2 (NVIDIA) | 7,804 | 12.09% |
| GeForce 7900 GTX (NVIDIA) | 6,962 | |
| Radeon X1900 GT (Connect3D) | 6,761 | 2.97% |
| GeForce 7900 GT OC (XFX) | 6,726 | 3.51% |
| Radeon X1900 XTX (ATI) | 6,699 | 3.93% |
| Radeon X1800 XT (ATI) | 6,534 | 6.55% |
| GeForce 7900 GT (NVIDIA) | 6,208 | 12.15% |
| GeForce 7800 GTX (MSI) | 6,067 | 14.75% |
| Radeon X1800 XL (ATI) | 5,554 | 25.35% |
| GeForce 7800 GT (NVIDIA) | 5,504 | 26.49% |
| GeForce 7600 GT (NVIDIA) | 4,780 | 45.65% |
| Radeon X850 XT P.E. (ATI) | 4,740 | 46.88% |
| GeForce 6800 GS (NVIDIA) | 4,130 | 68.57% |
| Radeon X1600 XT (ATI) | 4,085 | 70.43% |
| GeForce 6800 GT (NVIDIA) | 3,745 | 85.90% |
| Radeon X800 GTO (HIS) | 3,479 | 100.11% |
| Radeon X800 GT (HIS) | 3,192 | 118.11% |
| GeForce 7600 GS (NVIDIA) | 3,093 | 125.09% |
| Radeon X700 Pro (Sapphire) | 2,253 | 209.01% |
| GeForce 6600 GT (XFX) | 1,957 | 255.75% |
| GeForce 6600 (Albatron) | 1,259 | 452.98% |
| Radeon X600 Pro (Sapphire) | 1,040 | 569.42% |
| Radeon X600 XT (ATI) | 992 | 601.81% |
| 3DMark05 – 1600×1200 | Score | Difference |
| GeForce 7950 GX2 OC (XFX) | 7,749 | 18.14% |
| GeForce 7950 GX2 (NVIDIA) | 7,598 | 15.84% |
| GeForce 7900 GTX (NVIDIA) | 6,559 | |
| Radeon X1900 XTX (ATI) | 6,513 | 0.71% |
| Radeon X1900 GT (Connect3D) | 6,220 | 5.45% |
| GeForce 7900 GT OC (XFX) | 6,191 | 5.94% |
| Radeon X1800 XT (ATI) | 5,862 | 11.89% |
| GeForce 7900 GT (NVIDIA) | 5,524 | 18.74% |
| GeForce 7800 GTX (MSI) | 5,371 | 22.12% |
| GeForce 7800 GT (NVIDIA) | 4,786 | 37.05% |
| Radeon X1800 XL (ATI) | 4,785 | 37.07% |
| GeForce 7600 GT (NVIDIA) | 4,096 | 60.13% |
| Radeon X850 XT P.E. (ATI) | 3,931 | 66.85% |
| GeForce 6800 GS (NVIDIA) | 3,455 | 89.84% |
| Radeon X1600 XT (ATI) | 3,376 | 94.28% |
| GeForce 6800 GT (NVIDIA) | 3,091 | 112.20% |
| Radeon X800 GTO (HIS) | 2,856 | 129.66% |
| GeForce 7600 GS (NVIDIA) | 2,608 | 151.50% |
| Radeon X800 GT (HIS) | 2,430 | 169.92% |
| Radeon X700 Pro (Sapphire) | 1,789 | 266.63% |
| GeForce 6600 GT (XFX) | 1,264 | 418.91% |
| GeForce 6600 (Albatron) | 944 | 594.81% |
| Radeon X600 Pro (Sapphire) | 814 | 705.77% |
| Radeon X600 XT (ATI) | 708 | 826.41% |
| 3DMark05 – 1024×768 AAx4, Anisox4 | Score | Difference |
| GeForce 7950 GX2 OC (XFX) | 7,845 | 13.81% |
| GeForce 7950 GX2 (NVIDIA) | 7,735 | 12.22% |
| GeForce 7900 GTX (NVIDIA) | 6,893 | |
| Radeon X1800 XT (ATI) | 6,788 | 1.55% |
| Radeon X1900 XTX (ATI) | 6,717 | 2.62% |
| Radeon X1900 GT (Connect3D) | 6,656 | 3.56% |
| GeForce 7900 GT OC (XFX) | 6,655 | 3.58% |
| GeForce 7900 GT (NVIDIA) | 6,123 | 12.58% |
| GeForce 7800 GTX (MSI) | 6,052 | 13.90% |
| Radeon X1800 XL (ATI) | 5,874 | 17.35% |
| GeForce 7800 GT (NVIDIA) | 5,559 | 24.00% |
| Radeon X850 XT P.E. (ATI) | 4,971 | 38.66% |
| GeForce 7600 GT (NVIDIA) | 4,634 | 48.75% |
| GeForce 6800 GS (NVIDIA) | 4,108 | 67.79% |
| Radeon X1600 XT (ATI) | 4,072 | 69.28% |
| GeForce 6800 GT (NVIDIA) | 3,700 | 86.30% |
| Radeon X800 GTO (HIS) | 3,655 | 88.59% |
| Radeon X800 GT (HIS) | 3,523 | 95.66% |
| GeForce 7600 GS (NVIDIA) | 2,881 | 139.26% |
| Radeon X700 Pro (Sapphire) | 2,232 | 208.83% |
| GeForce 6600 GT (XFX) | 1,287 | 435.59% |
| Radeon X600 Pro (Sapphire) | 1,038 | 564.07% |
| GeForce 6600 (Albatron) | 935 | 637.22% |
| Radeon X600 XT (ATI) | 903 | 663.34% |
| 3DMark05 – 1280×1024 AAx4, Anisox4 | Score | Difference |
| GeForce 7950 GX2 OC (XFX) | 7,647 | 20.90% |
| GeForce 7950 GX2 (NVIDIA) | 7,485 | 18.34% |
| Radeon X1900 XTX (ATI) | 6,571 | 3.89% |
| GeForce 7900 GTX (NVIDIA) | 6,325 | |
| Radeon X1800 XT (ATI) | 6,040 | 4.72% |
| GeForce 7900 GT OC (XFX) | 5,968 | 5.98% |
| Radeon X1900 GT (Connect3D) | 5,955 | 6.21% |
| GeForce 7900 GT (NVIDIA) | 5,277 | 19.86% |
| GeForce 7800 GTX (MSI) | 5,186 | 21.96% |
| Radeon X1800 XL (ATI) | 4,915 | 28.69% |
| GeForce 7800 GT (NVIDIA) | 4,664 | 35.61% |
| Radeon X850 XT P.E. (ATI) | 4,028 | 57.03% |
| GeForce 7600 GT (NVIDIA) | 3,738 | 69.21% |
| Radeon X1600 XT (ATI) | 3,295 | 91.96% |
| GeForce 6800 GS (NVIDIA) | 3,286 | 92.48% |
| GeForce 6800 GT (NVIDIA) | 2,969 | 113.03% |
| Radeon X800 GTO (HIS) | 2,891 | 118.78% |
| Radeon X800 GT (HIS) | 2,510 | 151.99% |
| GeForce 7600 GS (NVIDIA) | 2,232 | 183.38% |
| Radeon X700 Pro (Sapphire) | 1,722 | 267.31% |
| Radeon X600 Pro (Sapphire) | 803 | 687.67% |
| Radeon X600 XT (ATI) | 581 | 988.64% |
| 3DMark05 – 1600×1200 AAx4, Anisox4 | Score | Difference |
| GeForce 7950 GX2 OC (XFX) | 7,447 | 31.39% |
| GeForce 7950 GX2 (NVIDIA) | 7,209 | 27.19% |
| Radeon X1900 XTX (ATI) | 6,253 | 10.32% |
| GeForce 7900 GTX (NVIDIA) | 5,668 | |
| Radeon X1800 XT (ATI) | 5,288 | 7.19% |
| Radeon X1900 GT (Connect3D) | 5,285 | 7.25% |
| GeForce 7900 GT OC (XFX) | 4,266 | 32.86% |
| Radeon X1800 XL (ATI) | 4,205 | 34.79% |
| GeForce 7800 GTX (MSI) | 4,168 | 35.99% |
| GeForce 7900 GT (NVIDIA) | 3,776 | 50.11% |
| GeForce 7800 GT (NVIDIA) | 3,746 | 51.31% |
| Radeon X850 XT P.E. (ATI) | 3,325 | 70.47% |
| Radeon X1600 XT (ATI) | 2,644 | 114.37% |
| GeForce 7600 GT (NVIDIA) | 2,553 | 122.01% |
| Radeon X800 GTO (HIS) | 2,365 | 139.66% |
| GeForce 6800 GS (NVIDIA) | 2,235 | 153.60% |
| GeForce 6800 GT (NVIDIA) | 2,233 | 153.83% |
| Radeon X800 GT (HIS) | 1,948 | 190.97% |
| GeForce 7600 GS (NVIDIA) | 1,552 | 265.21% |
| Radeon X700 Pro (Sapphire) | 1,374 | 312.52% |
| Radeon X600 Pro (Sapphire) | 589 | 862.31% |
| Radeon X600 XT (ATI) | 341 | 1,562.17% |
[nextpage title=”Doom 3″]Doom 3 is one of the heaviest games available today. As we’ve done on other programs, we ran this game at three resolutions: 1024x768x32, 1280x1024x32 and 1600x1200x32. This game allows several image quality levels and we’ve done our benchmarking on two levels, low and high. We ran demo1 four times and wrote the obtained number of frames per second. The first result we discarded at once, since it is far inferior than the other results. This happens because at the first time we run the demo the game must load all textures to video memory, fact that doesn’t happen from the second time we run the demo on. From the three results left, we consider as our official result the middle result, i.e., we discard the highest and the lowest values. Curiously almost all times the values obtained at the second round on were the same.
A very important detail that we must mention is that Doom 3 has an internal FPS lock: it is only capable of generating 60 frames per second, even if your board is able to produce more frames per second than that. This is done in order to make the game to have the same “playability” sensation independently from the video card installed on the PC. This lock, however, is disabled in the game benchmarking mode.
For further details on how to measure 3D performance with Doom 3, read our tutorial on this subject.
The results you check below. Keep in mind that models marked as “OC” are factory-overclocked. GeForce 7900 GT OC from XFX was running at 550 MHz with its memory being accessed at 1.63 GHz (815 MHz DDR) while the standard clock configuration for a GeForce 7900 GT is 450 MHz/1.32 GHz (660 MHz DDR). GeForce 7950 GX2 OC from XFX was running at 570 MHz with its memory being accessed at 1.55 GHz (775 MHz DDR) while the standard clock configuration for a GeForce 7950 GX2 is 500 MHz/1.2 GHz (600 MHz DDR).
| Doom 3 – 1024×768 Low | Score | Difference |
| Radeon X1900 XTX (ATI) | 96.7 | 1.68% |
| Radeon X1800 XT (ATI) | 95.9 | 0.84% |
| GeForce 7900 GT OC (XFX) | 95.2 | 0.11% |
| GeForce 7900 GTX (NVIDIA) | 95.1 | |
| GeForce 7900 GT (NVIDIA) | 94.7 | 0.42% |
| GeForce 7800 GTX (MSI) | 94.5 | 0.63% |
| Radeon X1800 XL (ATI) | 94.1 | 1.06% |
| GeForce 7800 GT (NVIDIA) | 94.1 | 1.06% |
| GeForce 7600 GT (NVIDIA) | 93.4 | 1.82% |
| GeForce 7950 GX2 (NVIDIA) | 92.2 | 3.15% |
| Radeon X1900 GT (Connect3D) | 92.1 | 3.26% |
| GeForce 6800 GS (NVIDIA) | 91.4 | 4.05% |
| GeForce 7950 GX2 OC (XFX) | 91.3 | 4.16% |
| Radeon X850 XT P.E. (ATI) | 84.5 | 12.54% |
| GeForce 6800 GT (NVIDIA) | 82.7 | 14.99% |
| GeForce 7600 GS (NVIDIA) | 79.5 | 19.62% |
| Radeon X800 GTO (HIS) | 77.1 | 23.35% |
| GeForce 6600 GT (XFX) | 75.9 | 25.30% |
| Radeon X800 GT (HIS) | 69.7 | 36.44% |
| Radeon X1600 XT (ATI) | 66.6 | 42.79% |
| Radeon X700 Pro (Sapphire) | 55.6 | 71.04% |
| GeForce 6600 (Albatron) | 54.1 | 75.79% |
| Radeon X600 XT (ATI) | 30.9 | 207.77% |
| Radeon X600 Pro (Sapphire) | 25.2 | 277.38% |
| Doom 3 – 1280×1024 Low | Score | Difference |
| GeForce 7900 GTX (NVIDIA) | 94.9 | |
| GeForce 7900 GT OC (XFX) | 94.1 | 0.85% |
| Radeon X1900 XTX (ATI) | 93.9 | 1.06% |
| GeForce 7950 GX2 OC (XFX) | 92.0 | 3.15% |
| GeForce 7900 GT (NVIDIA) | 91.6 | 3.60% |
| Radeon X1800 XT (ATI) | 91.4 | 3.83% |
| GeForce 7950 GX2 (NVIDIA) | 91.4 | 3.83% |
| GeForce 7800 GTX (MSI) | 90.4 | 4.98% |
| GeForce 7800 GT (NVIDIA) | 87.5 | 8.46% |
| Radeon X1900 GT (Connect3D) | 85.3 | 11.25% |
| GeForce 7600 GT (NVIDIA) | 82.2 | 15.45% |
| Radeon X1800 XL (ATI) | 80.8 | 17.45% |
| GeForce 6800 GS (NVIDIA) | 77.5 | 22.45% |
| Radeon X850 XT P.E. (ATI) | 76.6 | 23.89% |
| GeForce 6800 GT (NVIDIA) | 75.8 | 25.20% |
| GeForce 7600 GS (NVIDIA) | 61.5 | 54.31% |
| GeForce 6600 GT (XFX) | 59.9 | 58.43% |
| Radeon X800 GTO (HIS) | 55.1 | 72.23% |
| Radeon X800 GT (HIS) | 46.8 | 102.78% |
| Radeon X1600 XT (ATI) | 44.7 | 112.30% |
| Radeon X700 Pro (Sapphire) | 37.3 | 154.42% |
| GeForce 6600 (Albatron) | 36.6 | 159.29% |
| Radeon X600 XT (ATI) | 19.6 | 384.18% |
| Radeon X600 Pro (Sapphire) | 16.0 | 493.13% |
| Doom 3 – 1600×1200 Low | Score | Difference |
| GeForce 7900 GTX (NVIDIA) | 92.0 | |
| GeForce 7950 GX2 OC (XFX) | 91.8 | 0.22% |
| GeForce 7950 GX2 (NVIDIA) | 91.6 | 0.44% |
| GeForce 7900 GT OC (XFX) | 89.0 | 3.37% |
| Radeon X1900 XTX (ATI) | 86.6 | 6.24% |
| GeForce 7900 GT (NVIDIA) | 83.4 | 10.31% |
| GeForce 7800 GTX (MSI) | 80.8 | 13.86% |
| Radeon X1800 XT (ATI) | 77.5 | 18.71% |
| GeForce 7800 GT (NVIDIA) | 76.2 | 20.73% |
| Radeon X1900 GT (Connect3D) | 70.9 | 29.76% |
| GeForce 7600 GT (NVIDIA) | 69.1 | 33.14% |
| GeForce 6800 GT (NVIDIA) | 64.4 | 42.86% |
| GeForce 6800 GS (NVIDIA) | 63.4 | 45.11% |
| Radeon X1800 XL (ATI) | 63.1 | 45.80% |
| Radeon X850 XT P.E. (ATI) | 62.4 | 47.44% |
| GeForce 7600 GS (NVIDIA) | 46.2 | 99.13% |
| GeForce 6600 GT (XFX) | 45.9 | 100.44% |
| Radeon X800 GTO (HIS) | 38.9 | 136.50% |
| Radeon X1600 XT (ATI) | 31.7 | 190.22% |
| Radeon X800 GT (HIS) | 31.5 | 192.06% |
| GeForce 6600 (Albatron) | 26.5 | 247.17% |
| Radeon X700 Pro (Sapphire) | 25.5 | 260.78% |
| Radeon X600 XT (ATI) | 13.1 | 602.29% |
| Radeon X600 Pro (Sapphire) | 10.6 | 767.92% |
| Doom 3 – 1024×768 High | Score | Difference |
| Radeon X1800 XT (ATI) | 95.3 | 0.53% |
| GeForce 7900 GTX (NVIDIA) | 94.8 | |
| GeForce 7900 GT OC (XFX) | 94.8 | 0.00% |
| GeForce 7900 GT (NVIDIA) | 94.6 | 0.21% |
| GeForce 7800 GT (NVIDIA) | 94.4 | 0.42% |
| GeForce 7800 GTX (MSI) | 93.6 | 1.28% |
| GeForce 7600 GT (NVIDIA) | 92.3 | 2.71% |
| Radeon X1800 XL (ATI) | 92.2 | 2.82% |
| GeForce 7950 GX2 OC (XFX) | 92.1 | 2.93% |
| Radeon X1900 XTX (ATI) | 91.8 | 3.27% |
| GeForce 7950 GX2 (NVIDIA) | 91.7 | 3.38% |
| Radeon X1900 GT (Connect3D) | 90.9 | 4.29% |
| GeForce 6800 GS (NVIDIA) | 88.8 | 6.76% |
| Radeon X850 XT P.E. (ATI) | 83.6 | 13.40% |
| GeForce 6800 GT (NVIDIA) | 81.7 | 16.03% |
| GeForce 7600 GS (NVIDIA) | 76.5 | 23.92% |
| Radeon X800 GTO (HIS) | 73.8 | 28.46% |
| GeForce 6600 GT (XFX) | 70.8 | 33.90% |
| Radeon X800 GT (HIS) | 65.5 | 44.73% |
| Radeon X1600 XT (ATI) | 61.0 | 55.41% |
| Radeon X700 Pro (Sapphire) | 50.4 | 88.10% |
| GeForce 6600 (Albatron) | 48.7 | 94.66% |
| Radeon X600 XT (ATI) | 27.8 | 241.01% |
| Radeon X600 Pro (Sapphire) | 22.9 | 313.97% |
| Doom 3 – 1280×1024 High | Score | Difference |
| GeForce 7900 GTX (NVIDIA) | 94.9 | |
| Radeon X1900 XTX (ATI) | 94.8 | 0.11% |
| GeForce 7900 GT OC (XFX) | 93.8 | 1.17% |
| GeForce 7950 GX2 OC (XFX) | 91.6 | 3.60% |
| GeForce 7950 GX2 (NVIDIA) | 91.3 | 3.94% |
| GeForce 7900 GT (NVIDIA) | 91.2 | 4.06% |
| Radeon X1800 XT (ATI) | 90.2 | 5.21% |
| GeForce 7800 GTX (MSI) | 88.7 | 6.99% |
| GeForce 7800 GT (NVIDIA) | 86.7 | 9.46% |
| Radeon X1900 GT (Connect3D) | 82.4 | 15.17% |
| GeForce 7600 GT (NVIDIA) | 80.9 | 17.31% |
| Radeon X1800 XL (ATI) | 78.2 | 21.36% |
| Radeon X850 XT P.E. (ATI) | 74.4 | 27.55% |
| GeForce 6800 GS (NVIDIA) | 73.9 | 28.42% |
| GeForce 6800 GT (NVIDIA) | 72.4 | 31.08% |
| GeForce 7600 GS (NVIDIA) | 58.5 | 62.22% |
| GeForce 6600 GT (XFX) | 55.5 | 70.99% |
| Radeon X800 GTO (HIS) | 52.6 | 80.42% |
| Radeon X800 GT (HIS) | 44.4 | 113.74% |
| Radeon X1600 XT (ATI) | 41.7 | 127.58% |
| Radeon X700 Pro (Sapphire) | 34.4 | 175.87% |
| GeForce 6600 (Albatron) | 33.4 | 184.13% |
| Radeon X600 XT (ATI) | 18.4 | 415.76% |
| Radeon X600 Pro (Sapphire) | 15.0 | 532.67% |
| Doom 3 – 1600×1200 High | Score | Difference |
| GeForce 7900 GTX (NVIDIA) | 91.5 | |
| GeForce 7950 GX2 OC (XFX) | 91.4 | 0.11% |
| GeForce 7950 GX2 (NVIDIA) | 91.4 | 0.11% |
| Radeon X1900 XTX (ATI) | 88.4 | 3.51% |
| GeForce 7900 GT OC (XFX) | 88.3 | 3.62% |
| GeForce 7900 GT (NVIDIA) | 82.2 | 11.31% |
| GeForce 7800 GTX (MSI) | 79.9 | 14.52% |
| Radeon X1800 XT (ATI) | 75.8 | 20.71% |
| GeForce 7800 GT (NVIDIA) | 75.2 | 21.68% |
| Radeon X1900 GT (Connect3D) | 68.5 | 33.58% |
| GeForce 7600 GT (NVIDIA) | 67.8 | 34.96% |
| Radeon X1800 XL (ATI) | 61.4 | 49.02% |
| GeForce 6800 GT (NVIDIA) | 61.1 | 49.75% |
| GeForce 6800 GS (NVIDIA) | 60.6 | 50.99% |
| Radeon X850 XT P.E. (ATI) | 60.3 | 51.74% |
| GeForce 7600 GS (NVIDIA) | 44.2 | 107.01% |
| GeForce 6600 GT (XFX) | 43.4 | 110.83% |
| Radeon X800 GTO (HIS) | 37.7 | 142.71% |
| Radeon X800 GT (HIS) | 30.5 | 200.00% |
| Radeon X1600 XT (ATI) | 30.4 | 200.99% |
| GeForce 6600 (Albatron) | 25.0 | 266.00% |
| Radeon X700 Pro (Sapphire) | 24.1 | 279.67% |
| Radeon X600 XT (ATI) | 11.6 | 688.79% |
| Radeon X600 Pro (Sapphire) | 10.3 | 788.35% |
[nextpage title=”Far Cry”]
Far Cry is a game based on the new Shader 3.0 (DirectX 9.0c) programming model available on series 6 and 7 from NVIDIA and series X1000 from ATI graphics chips. We’ve updated the game to version 1.3.
As we’ve done on other programs, we ran this game at three resolutions, 1024x768x32, 1280x1024x32 and 1600x1200x32. This game allows several image quality levels and we’ve done our benchmarking on two levels, low and very high. To measure the performance we used the demo created by German magazine PC Games Hardware (PCGH), available at https://www.3dcenter.org/downloads/farcry-pcgh-vga.php. We run this demo four times and made an arithmetical average with the results. This average is the result presented in our graphs.
This game has a very important detail in its image quality configuration. Antialising, instead of being configured by numbers (1x, 2x, 4x or 6x) is configured as low, medium or high. The problem is that on NVIDIA chips both medium and high mean 4x, while on ATI chips medium means 2x and high means 6x, making the comparison between ATI and NVIDIA chips completely unfair. Because of that we configured antialising at 4x and anisotropic filtering at 8x manually at the video driver control panel.
For further details on how to measure 3D performance with Far Cry, read our tutorial on this subject.
The results you check below. Keep in mind that models marked as “OC” are factory-overclocked. GeForce 7900 GT OC from XFX was running at 550 MHz with its memory being accessed at 1.63 GHz (815 MHz DDR) while the standard clock configuration for a GeForce 7900 GT is 450 MHz/1.32 GHz (660 MHz DDR). GeForce 7950 GX2 OC from XFX was running at 570 MHz with its memory being accessed at 1.55 GHz (775 MHz DDR) while the standard clock configuration for a GeForce 7950 GX2 is 500 MHz/1.2 GHz (600 MHz DDR).
| Far Cry – 1024×768 Low | Score | Difference |
| Radeon X1900 GT (Connect3D) | 148.26 | 9.28% |
| Radeon X800 GT (HIS) | 145.56 | 7.29% |
| Radeon X850 XT P.E. (ATI) | 145.51 | 7.25% |
| Radeon X800 GTO (HIS) | 145.42 | 7.19% |
| Radeon X1800 XT (ATI) | 145.16 | 6.99% |
| Radeon X700 Pro (Sapphire) | 144.93 | 6.83% |
| Radeon X1800 XL (ATI) | 144.54 | 6.54% |
| Radeon X1600 XT (ATI) | 144.44 | 6.46% |
| Radeon X1900 XTX (ATI) | 144.02 | 6.15% |
| GeForce 7800 GTX (MSI) | 136.68 | 0.74% |
| GeForce 7600 GT (NVIDIA) | 136.43 | 0.56% |
| GeForce 7600 GS (NVIDIA) | 135.74 | 0.05% |
| GeForce 7900 GT OC (XFX) | 135.72 | 0.04% |
| GeForce 7900 GTX (NVIDIA) | 135.67 | |
| GeForce 7900 GT (NVIDIA) | 135.44 | 0.17% |
| GeForce 7800 GT (NVIDIA) | 134.94 | 0.54% |
| GeForce 6800 GS (NVIDIA) | 134.93 | 0.55% |
| Radeon X600 XT (ATI) | 132.76 | 2.19% |
| GeForce 7950 GX2 OC (XFX) | 131.69 | 3.02% |
| GeForce 7950 GX2 (NVIDIA) | 131.48 | 3.19% |
| GeForce 6600 GT (XFX) | 130.43 | 4.02% |
| GeForce 6600 (Albatron) | 123.60 | 9.77% |
| GeForce 6800 GT (NVIDIA) | 120.56 | 12.53% |
| Radeon X600 Pro (Sapphire) | 112.52 | 20.57% |
| Far Cry – 1280×1024 Low | Score | Difference |
| Radeon X1900 GT (Connect3D) | 145.00 | 8.95% |
| Radeon X850 XT P.E. (ATI) | 143.19 | 7.59% |
| Radeon X800 GT (HIS) | 142.98 | 7.43% |
| Radeon X800 GTO (HIS) | 142.41 | 7.00% |
| Radeon X1800 XL (ATI) | 141.73 | 6.49% |
| Radeon X1800 XT (ATI) | 140.71 | 5.73% |
| Radeon X1600 XT (ATI) | 140.49 | 5.56% |
| Radeon X700 Pro (Sapphire) | 138.43 | 4.01% |
| GeForce 7800 GTX (MSI) | 133.27 | 0.14% |
| GeForce 7600 GT (NVIDIA) | 133.24 | 0.11% |
| GeForce 7900 GTX (NVIDIA) | 133.09 | |
| GeForce 6800 GS (NVIDIA) | 132.52 | 0.43% |
| GeForce 7900 GT (NVIDIA) | 132.32 | 0.58% |
| GeForce 7900 GT OC (XFX) | 132.16 | 0.70% |
| GeForce 7600 GS (NVIDIA) | 131.86 | 0.93% |
| GeForce 7800 GT (NVIDIA) | 131.78 | 0.99% |
| Radeon X1900 XTX (ATI) | 131.03 | 1.57% |
| GeForce 7950 GX2 (NVIDIA) | 127.99 | 3.98% |
| GeForce 7950 GX2 OC (XFX) | 127.89 | 4.07% |
| GeForce 6800 GT (NVIDIA) | 127.71 | 4.21% |
| GeForce 6600 GT (XFX) | 127.24 | 4.60% |
| Radeon X600 XT (ATI) | 89.16 | 49.27% |
| GeForce 6600 (Albatron) | 87.83 | 51.53% |
| Radeon X600 Pro (Sapphire) | 72.96 | 82.42% |
| Far Cry – 1600×1200 Low | Score | Difference |
| Radeon X1900 GT (Connect3D) | 145.81 | 8.79% |
| Radeon X850 XT P.E. (ATI) | 143.59 | 7.13% |
| Radeon X1800 XT (ATI) | 142.30 | 6.17% |
| Radeon X1800 XL (ATI) | 141.82 | 5.81% |
| Radeon X800 GTO (HIS) | 139.29 | 3.92% |
| GeForce 7900 GTX (NVIDIA) | 134.03 | |
| GeForce 7600 GT (NVIDIA) | 133.96 | 0.05% |
| GeForce 7800 GTX (MSI) | 133.93 | 0.07% |
| GeForce 7900 GT OC (XFX) | 133.71 | 0.24% |
| GeForce 7900 GT (NVIDIA) | 133.59 | 0.33% |
| GeForce 7800 GT (NVIDIA) | 133.18 | 0.64% |
| GeForce 6800 GS (NVIDIA) | 132.30 | 1.31% |
| Radeon X1900 XTX (ATI) | 130.85 | 2.43% |
| GeForce 7950 GX2 OC (XFX) | 128.99 | 3.91% |
| GeForce 7950 GX2 (NVIDIA) | 128.38 | 4.40% |
| Radeon X800 GT (HIS) | 128.32 | 4.45% |
| GeForce 6800 GT (NVIDIA) | 127.64 | 5.01% |
| Radeon X1600 XT (ATI) | 121.01 | 10.76% |
| GeForce 6600 GT (XFX) | 109.30 | 22.63% |
| GeForce 7600 GS (NVIDIA) | 108.98 | 22.99% |
| Radeon X700 Pro (Sapphire) | 105.22 | 27.38% |
| GeForce 6600 (Albatron) | 63.37 | 111.50% |
| Radeon X600 XT (ATI) | 59.82 | 124.06% |
| Radeon X600 Pro (Sapphire) | 48.85 | 174.37% |
| Far Cry – 1024×768 Very High | Score | Difference |
| Radeon X1900 GT (Connect3D) | 78.79 | 4.57% |
| Radeon X850 XT P.E. (ATI) | 76.61 | 1.67% |
| Radeon X1800 XL (ATI) | 76.55 | 1.59% |
| Radeon X1800 XT (ATI) | 76.18 | 1.10% |
| GeForce 7800 GT (NVIDIA) | 75.82 | 0.62% |
| GeForce 7800 GTX (MSI) | 75.38 | 0.04% |
| GeForce 7900 GTX (NVIDIA) | 75.35 | |
| GeForce 7900 GT (NVIDIA) | 74.65 | 0.94% |
| GeForce 7900 GT OC (XFX) | 73.93 | 1.92% |
| GeForce 7950 GX2 OC (XFX) | 73.31 | 2.78% |
| GeForce 7950 GX2 (NVIDIA) | 73.03 | 3.18% |
| GeForce 7600 GT (NVIDIA) | 72.70 | 3.65% |
| GeForce 6800 GS (NVIDIA) | 70.72 | 6.55% |
| Radeon X1900 XTX (ATI) | 69.40 | 8.57% |
| GeForce 6800 GT (NVIDIA) | 67.93 | 10.92% |
| Radeon X800 GTO (HIS) | 63.05 | 19.51% |
| Radeon X800 GT (HIS) | 54.82 | 37.45% |
| GeForce 7600 GS (NVIDIA) | 48.28 | 56.07% |
| Radeon X1600 XT (ATI) | 47.91 | 57.27% |
| Radeon X700 Pro (Sapphire) | 40.72 | 85.04% |
| GeForce 6600 GT (XFX) | 38.28 | 96.84% |
| GeForce 6600 (Albatron) | 23.67 | 218.34% |
| Radeon X600 Pro (Sapphire) | 20.41 | 269.18% |
| Radeon X600 XT (ATI) | 18.74 | 302.08% |
| Far Cry – 1280×1024 Very High | Score | Difference |
| Radeon X1800 XT (ATI) | 75.28 | 2.69% |
| GeForce 7900 GTX (NVIDIA) | 73.31 | |
| GeForce 7900 GT OC (XFX) | 72.96 | 0.48% |
| GeForce 7900 GT (NVIDIA) | 71.77 | 2.15% |
| GeForce 7950 GX2 (NVIDIA) | 71.17 | 3.01% |
| GeForce 7800 GTX (MSI) | 71.13 | 3.06% |
| GeForce 7950 GX2 OC (XFX) | 71.13 | 3.06% |
| Radeon X1900 GT (Connect3D) | 71.03 | 3.21% |
| Radeon X1800 XL (ATI) | 70.00 | 4.73% |
| Radeon X1900 XTX (ATI) | 68.59 | 6.88% |
| Radeon X850 XT P.E. (ATI) | 67.93 | 7.92% |
| GeForce 7800 GT (NVIDIA) | 67.09 | 9.27% |
| GeForce 7600 GT (NVIDIA) | 53.88 | 36.06% |
| GeForce 6800 GS (NVIDIA) | 53.81 | 36.24% |
| GeForce 6800 GT (NVIDIA) | 51.53 | 42.27% |
| Radeon X800 GTO (HIS) | 45.80 | 60.07% |
| Radeon X800 GT (HIS) | 38.43 | 90.76% |
| Radeon X1600 XT (ATI) | 35.59 | 105.98% |
| GeForce 7600 GS (NVIDIA) | 31.41 | 133.40% |
| Radeon X700 Pro (Sapphire) | 28.20 | 159.96% |
| GeForce 6600 GT (XFX) | 25.82 | 183.93% |
| GeForce 6600 (Albatron) | 15.07 | 386.46% |
| Radeon X600 Pro (Sapphire) | 14.15 | 418.09% |
| Radeon X600 XT (ATI) | 13.62 | 438.25% |
| Far Cry – 1600×1200 Very High | Score | Difference |
| GeForce 7950 GX2 OC (XFX) | 72.35 | 1.09% |
| Radeon X1800 XT (ATI) | 71.88 | 0.43% |
| GeForce 7950 GX2 (NVIDIA) | 71.70 | 0.18% |
| GeForce 7900 GTX (NVIDIA) | 71.57 | |
| GeForce 7900 GT OC (XFX) | 69.37 | 3.17% |
| Radeon X1900 XTX (ATI) | 68.62 | 4.30% |
| Radeon X1900 GT (Connect3D) | 60.12 | 19.05% |
| GeForce 7900 GT (NVIDIA) | 59.50 | 20.29% |
| Radeon X1800 XL (ATI) | 59.36 | 20.57% |
| GeForce 7800 GTX (MSI) | 58.10 | 23.18% |
| Radeon X850 XT P.E. (ATI) | 54.23 | 31.97% |
| GeForce 7800 GT (NVIDIA) | 52.35 | 36.71% |
| GeForce 6800 GS (NVIDIA) | 39.93 | 79.24% |
| GeForce 7600 GT (NVIDIA) | 39.62 | 80.64% |
| GeForce 6800 GT (NVIDIA) | 34.29 | 108.72% |
| Radeon X800 GTO (HIS) | 34.06 | 110.13% |
| Radeon X800 GT (HIS) | 27.74 | 158.00% |
| Radeon X1600 XT (ATI) | 24.51 | 192.00% |
| GeForce 7600 GS (NVIDIA) | 22.78 | 214.18% |
| Radeon X700 Pro (Sapphire) | 20.01 | 257.67% |
| GeForce 6600 GT (XFX) | 19.53 | 266.46% |
| GeForce 6600 (Albatron) | 11.28 | 534.49% |
| Radeon X600 Pro (Sapphire) | 8.04 | 790.17% |
| Radeon X600 XT (ATI) | 7.01 | 920.97% |
[nextpage title=”Conclusions”]
GeForce 7900 GTX showed to be a true high-end chip, as expected. Unfortunately we didn’t have a Radeon X1900 XT from ATI for a direct comparison, which would make this review even more complete. Compared to Radeon X1900 XTX we have no doubt on which video card is the best.
GeForce 7900 GTX was between 4% and 12% faster than Radeon X1900 XTX on 3DMark03, while they both achieved a similar performance on other programs we used, sometimes with a small advantage (i.e., up to 8%) to NVIDIA’s part. Radeon X1900 XTX was faster only on 3DMark05 at 1600×1200 with image quality settings enabled (10% faster).
Then comes pricing. At Shopping.com GeForce 7900 GTX is quoted, on average, at USD 500, while Radeon X1900 XTX is quoted, on average, at USD 600. That’s a huge difference.
Of course we are talking about arithmetic averages, i.e., we take the lower price, add to the higher price and divide them by 2. You can find both cards being sold by less. The lower price we’ve seen for GeForce 7900 GTX was USD 450 (a model from eVGA at TigerDirect.com) while the cheapest Radeon X1900 XTX models can be found at USD 500 (TigerDirect.com carries a model from HIS costing USD 470, though).
Deciding between a GeForce 7900 GTX and a Radeon X1900 XTX is a no-brainer: go for the NVIDIA model.
So, if you are looking for the most very high-end video card for playing games at very high resolutions with all image quality settings enabled and don’t want the “GT” models, GeForce 7900 GTX is the right choice.
Of course for the average user, GeForce 7900 GT carries a far better cost/benefit ratio, as it costs “only” USD 270, providing a great performance for the normal user. Of course GTX is faster, but performance depends a lot on the program used. On Far Cry, for example, GTX was faster than GT only at 1600×1200 enabling image quality settings and on Doom 3 GTX was faster than GT only at 1600×1200. On 3DMark03, however, GTX was between 20% and 35% faster, and on 3DMark05 GTX was between 7% and 50% faster.
If you are a hardcore gamer and don’t want to spend USD 600 or more on a GeForce 7900 GX2, GeForce 7900 GTX is the video card you are looking for. However, if you are a true gamer but don’t want to spend between USD 450 and USD 500 on a video card, GeForce 7900 GT – which can be easily found at USD 270 range – is the video card for you.