GPUBoss Review Our evaluation of 6970 vs 750 Ti among Desktop GPUs

Gaming

Battlefield 3, Battlefield 4, Bioshock Infinite and 21 more

Graphics

T-Rex, Manhattan, Cloud Gate Factor, Sky Diver Factor and 1 more

Computing

Face Detection, Ocean Surface Simulation and 3 more

Performance per Watt

Battlefield 3, Battlefield 4, Bioshock Infinite and 32 more

Value

Battlefield 3, Battlefield 4, Bioshock Infinite and 32 more

Noise and Power

TDP, Idle Power Consumption, Load Power Consumption and 2 more

6.2

Overall Score

Winner
AMD Radeon HD 6970 

GPUBoss recommends the AMD Radeon HD 6970  based on its benchmarks.

See full details

Cast your vote Do you agree or disagree with GPUBoss?

Thanks for adding your opinion. Follow us on Facebook to stay up to date with the latest news!
VS

AMD Radeon HD 6970

GPUBoss Winner
Front view of Radeon HD 6970

Differences What are the advantages of each

Front view of Radeon HD 6970

Reasons to consider the
AMD Radeon HD 6970

Report a correction
Much better 3DMark06 score 24,035 vs 5,378 Around 4.5x better 3DMark06 score
Significantly higher memory bandwidth 176 GB/s vs 86.4 GB/s More than 2x higher memory bandwidth
Better floating-point performance 2,703 GFLOPS vs 1,728 GFLOPS More than 55% better floating-point performance
Significantly more shading units 1,536 vs 640 896 more shading units
Significantly more texture mapping units 96 vs 40 56 more texture mapping units
More render output processors 32 vs 16 Twice as many render output processors
Higher pixel rate 28.16 GPixel/s vs 16.32 GPixel/s Around 75% higher pixel rate
Significantly higher battlefield 4 framerate 90 vs 35 More than 2.5x higher battlefield 4 framerate
Wider memory bus 256 bit vs 128 bit 2x wider memory bus
Front view of GeForce GTX 750 Ti

Reasons to consider the
Nvidia GeForce GTX 750 Ti

Report a correction
Higher clock speed 1,020 MHz vs 880 MHz More than 15% higher clock speed
Better T-Rex score 2.93 frames/s vs 1.83 frames/s Around 60% better T-Rex score
Much lower TDP 60W vs 250W 4.2x lower TDP
Higher memory clock speed 1,502 MHz vs 1,375 MHz Around 10% higher memory clock speed
Better PassMark direct compute score 1,830 vs 1,399 More than 30% better PassMark direct compute score

Benchmarks Real world tests of Radeon HD 6970 vs GeForce GTX 750 Ti

Bitcoin mining Data courtesy CompuBench

Radeon HD 6970
274.06 mHash/s
GeForce GTX 750 Ti
182.53 mHash/s

Face detection Data courtesy CompuBench

Radeon HD 6970
18.68 mPixels/s
GeForce GTX 750 Ti
56.77 mPixels/s

T-Rex (GFXBench 3.0) Data courtesy CompuBench

Manhattan (GFXBench 3.0) Data courtesy CompuBench

Fire Strike Factor Data courtesy FutureMark

Sky Diver Factor Data courtesy FutureMark

Battlefield 4

Battlefield 3

Reviews Word on the street

Comments

Showing 3 comments.
Too much heat, too much noise, costed WAY too much at release($400 vs $150), and with modern optimizations from Nvidia, the 750 Ti ties or beats it in most popular games. C'mon, it's not exactly fast, about 70% the performance of a GTX 580. 750 Ti is quieter, cooler, cheaper, easier to install on low-end systems because it's smaller, lighter, and can take it's power through the PCIe slot instead of needing 2 power connectors from the PSU. 6970 is nice for... Crossfire? If you have $800 to drop on a low-end gaming setup?
Yea, its ridiculous really. Though I would hope that if they are really comparing cards and deciding what to purchase/keep using as a consumer that they would take a look at more then just the end results that declares the supposed winner. Unfortunately there a quite a few will use these posted "results" of which card won as to what gpu they should buy or whether they should "upgrade" or not. They will claim no bias on way or the other, but there shouldn't be a surprise when someone claims that gpuboss is bias. Comparison tests like these are definitely the reason for such claims, I mean really the winner of a GPU comparison wins based on its "noise and power"?. It is already misleading imo with it being called "noise and power" instead of "noise and power consumption". Making it seem as if the 750ti was declared a winner here on gpuboss because its not only quieter but is a more powerful card then the HD 6970 which it is not. Noise and power use are not irrelevant, but they really have no bearing on how the gpu will perform. However when said card (750ti) does not really win and much if any of the relevant performance tests they still somehow put it as the better card. It gets beaten in all but one of the benchmarks shown, and shows quite a few reasons (all related to performance) to consider the hd 6970 over the 750ti you have to wonder if there is really no bias at all as to why the 750ti won based on its "nose and power", when they themselves list so many reasons (ones that tend to be important to gpu shopping) to choose the hd 6970.
why are these discussions so biased in favor of Nvidia? The GTX 750 ti only out scores in two areas that are irrelevant to performance and it is better? Hands down the HD 6970 blows the GTX 750 ti out of the water without even breaking a sweat! I have had both cards in the same system and have used both cards in a few others and every time the Radeon card kills the Nvidia one.
comments powered by Disqus