Benchmarking is a good way to get a general idea of the performance of your device. That said, it does not really mean much at all. You’ll see a lot of people in forums complaining that they can’t reach some number. Or even better, when the tools update to provide more accurate results, people will continue to use the old versions to keep their scores higher.

Benchmarks should be used only as a guideline, not the absolute performance of your phone. My rule has always been, “does my phone (or computer for that matter) perform as well as I want it to?” Don’t get bent up on trying to get the highest numbers possible. Just because someone else got some ridiculous score, doesn’t mean you need to. I like real use benchmarks. This means, I don’t disable normal services, or use SetCPU to modify performance while the test runs. What good does that do for you? Don’t you want to see benchmarking of how your phone performs under normal circumstances?

The two most common tools used are Quadrant & Linpack.

  • Quadrant – Measures the following, then calculates a score and graphs it in comparison to other known “stock” scores.
  • * CPU – arithmetic operations, XML parsing, multimedia decoding
    * Memory throughput
    * I/O – filesystem access and database operations
    * 2D graphics
    * 3D graphics – OpenGL single-pass and multi-pass rendering with stencil buffers

  • Linpack – Simply calculates the Millions of FLoating-point Operations Per Second (MFLOPS). This score can be compared to the top android devices in the application.
  • The LINPACK Benchmarks are a measure of a system’s floating point computing power. Introduced by Jack Dongarra, they measure how fast a computer solves a dense N by N system of linear equations Ax = b, which is a common task in engineering. The solution is obtained by Gaussian elimination with partial pivoting, with 2/3*N3 + 2*N2 floating point operations. The result is reported in Millions of FLoating-point Operations Per Second (MFLOP/s, sometimes simply called FLOPS).

    This test is more a reflection of the state of the Android Dalvik Virtual Machine than of the floating point performance of the underlying processor. Software written for an Android device is written using Java code that the Dalvik VM interprets at run time.