MobileNews

Geekbench removes four years of Samsung Galaxy benchmarks following GOS ‘throttling’ debacle [U]

Benchmarks are never fully indicative of how a device will actually perform in real life, but they can provide some useful points of comparison between closely matched devices. Geekbench, one of the best benchmarking apps available across platforms, has just announced that it will remove results from the past few years of Samsung Galaxy devices over a recent software debacle.

Last week Samsung’s “Game Optimizing Service” came to light as an app that was apparently throttling games on Samsung’s Galaxy smartphones, and also thousands of other Android apps. The obvious reason was for the sake of battery life, but the behavior was met with scrutiny largely because Samsung excluded all benchmark apps from the limiting.

As a result, Geekbench announced on Twitter on Friday that it would remove most recent Samsung Galaxy benchmark results from its library, with the Galaxy S10, S20, S21, and S22 series’ all included in the removals. It’s explained that Samsung’s behavior is viewed as “benchmark manipulation,” which in the past has resulted in removing benchmarks from OnePlus and others who have attempted similar actions.

Samsung has responded to user complaints regarding its GOS, saying that a future update will allow users more control over how the GOS affects games. However, Samsung refuted clear evidence showing that non-gaming Android apps are throttled by the GOS, saying that the service does not adjust performance on normal apps.


Update 3/15: Following a tip from the folks over at Android Police, Geekbench has also delisted the Galaxy Tab S8 series from its benchmark results, and the device probably won’t return in the future.


More on Samsung:


Check out the latest Samsung phones at great prices from Gizmofashion – our recommended retail partner.


Author: Ben Schoon
Source: 9TO5Google

Related posts
AI & RoboticsNews

Medical training’s AI leap: How agentic RAG, open-weight LLMs and real-time case insights are shaping a new generation of doctors at NYU Langone

AI & RoboticsNews

OpenAI’s ChatGPT explodes to 400M weekly users, with GPT-5 on the way

AI & RoboticsNews

Together AI’s $305M bet: Reasoning models like DeepSeek-R1 are increasing, not decreasing, GPU demand

DefenseNews

Army Stinger missile replacement competition heads into flight tests

Sign up for our Newsletter and
stay informed!