Samsung has been caught cheating on benchmark tests once again and this time with the Galaxy Note 3. Previously it was the Samsung Galaxy S4 that was caught in the middle of this controversy.
ArsTechnica has done a detailed post on how Samsung Galaxy Note 3’s US version with the Qualcomm’s Snapdragon quad-core processor clocked at 2.3 GHz, seems to have set to show higher benchmark scores for some standard tests.
Benchmark tests usually involve running a set of programmes, operations, on a computing device such as a laptop, PC or even a smartphone now, in order to assess its relative performance.Some popular benchmark tests for smartphones include: Geekbench, Antutu, Google’s Octane etc.
According to the post on Ars, it appears that Samsung’s Galaxy Note 3 has been programmed to show higher results for certain benchmark tests. The report says that Samsung appears to be artificially boosting the US Note 3’s benchmark scores with a special, high-power CPU mode that kicks in when the device runs a large number of popular benchmarking apps.
The post on Ars, pointed out that the Note 3 and LG G2 have the same processor yet the Note 3 was outdoing the G2 by almost 20 percent on the tests. After some testing, it appeared that the boosted benchmark mode is triggered by the package names of the most popular benchmarking apps-loading Geekbench, for example, starts this mode, notes the report.
In fact, when Ars ran a slightly altered version of Geekbench where they just changed the package name of the app to Stealthbench, the scores dropped.
The post goes on to note, “With Geekbench, System Monitor shows that the CPU is locked into 2.3GHz 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.”
Sadly, the Ars team also pointed out that Samsung didn’t have to resort to this benchmark boosting as the phone was faster than the LG G2 even without the special mode.
Previously AnandTech had pointed out how Samsung’s Galaxy S4 was optimised to give certain results for some benchmark tests. The report had noted that “select benchmarks, the CPU is set to the maximum CPU frequency available at app launch,”where the Samsung Galaxy S4 was concerned.
Samsung had then responded to The Verge saying they “did not use a specific tool on purpose to achieve higher benchmark scores.”
Rigging benchmark tests was pretty common in the PC and Laptop era and the same thing is being repeated with smartphones. Perhaps the only solution is to ensure that benchmark results are not the sole criteria on which a smartphone is judged.