Samsung Cheats Again By Artificially Boosting Note 3’s Benchmark Scores

IMG 26197 640x520

Back in July, Samsung was caught manipulating the Galaxy S4 to obtain repeatedly high results on certain benchmark tests and now, the Korean company appears to be artificially boosting the Galaxy Note 3’s benchmark scores with a special, high-power CPU mode that kicks in only when the device runs popular benchmarking apps, according to ArsTechnica. Apple’s marketing chief Phil Schiller also highlighted the report in a tweet earlier today, calling them “shenanigans “.

 

Ars notes that a quick comparison of Galaxy Note 3’s scores to the similarly-specced LG G2 made it clear to them that something fishy was going on. It seems when the Note 3 is idling, three of the four cores shut off to conserve power; the remaining core drops down to a low-power 300MHz mode. However, when any popular CPU benchmarking app is loaded, the Note 3 CPU locks into 2.3GHz mode, the fastest speed possible, and none of the cores ever shut off. Benchmarks exist to measure the performance of a phone during normal usage, and a device should never treat a benchmark app differently than a normal one.

Sli1de1 2 640x480

To further prove Samsung’s dishonesty, here’s what they did to trick the phone into not entering a special “benchmark mode” during a benchmark:

“A bit of testing showed that the device’s boosted benchmark mode is triggered by the package names of the most popular benchmarking apps—loading Geekbench, for example, starts this mode. So we slapped together “Stealthbench,” a renamed version of Geekbench 3. By disassembling the benchmarking app, changing only the package name, and reassembling it, we could run the app without the CPU knowing we were running a benchmark app. The Note 3 should treat our benchmark like any other app and give a true representation of the phone’s performance relative to other devices.

Above is a picture of Geekbench and of Stealthbench, which is identical to Geekbench in every way except for a different package name. With Geekbench, System Monitor shows the CPU is locked into 2.3 GHz mode and all cores are active, but in Stealthbench, the CPU is allowed to idle, shut off cores, and switch power modes, the same way it does in any other app. We have successfully disabled the special benchmark mode. 

The difference is remarkable. In Geekbench’s multicore test, the Note 3’s benchmark mode gives the device a 20 percent boost over its “natural” score. With the benchmark boosting logic stripped away, the Note 3 drops down to LG G2 levels, which is where we initially expected the score to be given the identical SoCs.

Funny thing is, even with the benchmark booster disabled, the Note 3 comes out faster than the LG Optimus G2 in this test. Who knows what Samsung really intended by artificially boosting the benchmarks on its latest phablet, something that wasn’t even necessary in the first place.

What do you think?

“Technology runs through my veins...” | Follow me: @DrUsmanQ usman@iPhoneinCanada.ca

  • smithy

    not apple related?

  • JMCD23

    This is pretty standard practice as far as I’m aware of. Nvidia/AMD have been doing this for years for things like 3dmark. This is just pushing the performance results for the highest number. It just demonstrates what the phone is capable of. Benchmarks aren’t real world performance anyway, no one should ever take them as that. There is nothing wrong with this.

  • Samsung is a major Apple competitor, so this is directly related. The facts are the company was busted twice for doping its benchmarks. Not sure why but those are the facts uncovered by others.

  • smackza

    BZZZZZ! Wrong answer shamesung apologizer.

  • smackza

    Oh samcrap, why do you suck so hard? Ya know, you really don’t have to be such a cumtwat. Something to think about…

  • Spotanidiot@idiot.com

    You are an idiot.

  • JMCD23

    Are you going to provide any actual argument? Benchmarks are test in a asynthetic environment. They’re supposed to show maximum theoretical performance. So all the big chip manufacturers have been cheating for over a decade too huh?

  • Farids

    In the industry, hardware makers, design their hardware to take advantage of the testing software’s methods of benchmarking, and fool the software into showing higher readings. But actually making the hardware go on turbo as soon as it sniffs a benchmark software around? Shame! It is like going to buy a sports car. You open the hood, test the engine, find it has 500 horse powers. You go ahead and buy the car, only to find the engine is 100 horsepower less than the test and what the seller claimed. This is not the first time as Samsung has a bad track record of cheating customers. Couple of years ago, Samsung presented the world with Galaxy S3. At the time, it was the most advanced, most capable and most powerful phone. Then at the time of release, Samsung sold another different phone, almost half as powerful as what they had shown (CPU, RAM etc.) in the same case as the device they demoed, called it Samsung Galaxy S3, and sold it to the world!!! Bad track record for a company that wants to lead the industry!