Is Samsung optimising Galaxy S4 to bump up benchmark tests?

Is Samsung optimising its processor so that it reflects a certain benchmark on AnTuTu and GLBenchmark but doesn’t hold up for other tests? According to reports on AnandTech and posts from Beyond3D forum, the smartphone manufacturer appears to be doing just that. The post on  Beyond3D forum, which was put up by a user named   Nebuchadnezzar, pointed out that when he was testing the Samsung Exynos 5 Octa processor when he found out that the chip’s GPU hit the 532MHz on AnTuTu and GLBenchmark test. For all the other apps, the GPU clocked only 480MHz. (A Graphic Processing  Unit’s (GPU) clock speed is the speed at which a microprocessor executes instructions and it is measured in megahertz.) [caption id=“attachment_999971” align=“alignleft” width=“380”] Samsung Galaxy S4 in this file photo. Reuters[/caption] According to the user, Samsung is reserving the higher benchmark for the two standard tests and has optimised the processor for them. Meanwhile a post on Anand Tech has also confirmed that the r_unning any games, even the most demanding titles, returned a GPU frequency of 480MHz._ However,  the post also points out that, Samsung never publicly claimed max GPU frequencies for the Exynos 5 Octa. So technically, you can’t accuse Samsung of lying since they never made any claims.   The report on AnandTech also says that the old GLBenchmark version (2.5.1) appears to be singled out as a benchmark that is allowed to run the GPU at the higher frequency/voltage setting. The new one is clocking at 480 MHz. As far as the processor of the Samsung Galaxy S4 is concerned, the Exynos 5 Octa has four high-performance ARM Cortex-A15 cores and four low-power ARM Cortex-A7 cores. It comes in two versions: the 5410, which contains an Imagination Technologies PowerVR SGX544MP3 GPU, and the 5420, which uses an ARM Mali-T628 MP6 GPU. Nebuchadnezzar and both Anand Tech tested the 5410 GPU which is much more powerful. Meanwhile Samsung has responded to these allegations and claimed that it is innocent. According to The Verge Samsung said that they “did not use a specific tool on purpose to achieve higher benchmark scores.” It added “under normal conditions, the Galaxy S4 operates up to 533MHz at its best performance and certain “full screen apps” (any app in which the status bar isn’t present) such as the camera, browser, video player, and benchmarking tools, are classified as requiring the highest performance available.” The question is did Samsung cheat on tests? If the conclusions of the AnandTech are right it would be appear so. It also proves that the benchmark test can never accurately tell how a phone will perform in daily use.