CrystalDiskMark vs Quickbench

CrystalDiskMark is Windows software for benchmarking disk and storage performance. It measures sequential and random read, write and mixed workloads, with Peak, Real World and Demo measurement modes. Users can create custom test profiles, and results can be exported as UTF-16LE text with a BOM, PNG, JPEG or BMP. The download page lists Standard, Aoi and Shizuku editions; Standard is available as an installer, ZIP or source code. Listed system support spans Windows XP through Windows 11 and Windows Server 2003 through 2025, across x86, x64 and ARM64. However, the installer and x64 version do not support XP or Server 2003. The maker warns that benchmarking may shorten SSD or USB memory life and that results cannot be compared across different major versions. Results may also vary with test file size and position, fragmentation, storage controller, CPU speed and, for some SSDs, test data pattern. The free desktop edition costs nothing. A separate Microsoft Store edition costs 9.99 USD once.

Quickbench is a free Bash script for measuring basic performance on Linux-based hosts, including virtual machines. It reports CPU configuration and runs busy-loop benchmarks at different parallel job counts, returning loop rates. Memory checks report Linux-allocatable memory and run a simple bandwidth test that may reflect L1 or L2 cache performance. Storage checks use parallel dd transfers with 4k and 1M blocks, reporting bandwidth and I/O rates. They run on the filesystem in the current working directory; to measure another device, mount its filesystem there and run Quickbench from that location. The script is designed for minimal Linux servers and needs no specific dependencies. It takes one parameter: the maximum duration in seconds for each benchmark loop. The project recommends at least 30 seconds for statistically meaningful results and cautions that values below 10 seconds may be unreliable. CPU loop measurements are not calibrated, so comparisons call for matching Quickbench, kernel, Bash, and dd versions. The project describes storage testing as non-thorough and says it cannot measure I/O completion latency. It is licensed under GPL-3.0.