Also found in: Dictionary, Thesaurus, Medical, Legal, Financial, Acronyms, Idioms, Wikipedia.


A relatively permanent natural or artificial object bearing a marked point whose elevation above or below an adopted datum—for example, sea level—is known. Abbreviated BM.
(industrial engineering)
A standard of measurement possessing sufficient identifiable characteristics common to the individual units of a population to facilitate economical and efficient comparison of attributes for units selected from a sample.
(science and technology)
A reference value against which a measurement or a series of measurements may be compared.


A permanent reference mark, fixed to a building or to the ground, whose height above a standard datum level has been accurately determined by survey.


A standard program or set of programs which can be run on different computers to give an inaccurate measure of their performance.

"In the computer industry, there are three kinds of lies: lies, damn lies, and benchmarks."

A benchmark may attempt to indicate the overall power of a system by including a "typical" mixture of programs or it may attempt to measure more specific aspects of performance, like graphics, I/O or computation (integer or floating-point). Others measure specific tasks like rendering polygons, reading and writing files or performing operations on matrices. The most useful kind of benchmark is one which is tailored to a user's own typical tasks. While no one benchmark can fully characterise overall system performance, the results of a variety of realistic benchmarks can give valuable insight into expected real performance.

Benchmarks should be carefully interpreted, you should know exactly which benchmark was run (name, version); exactly what configuration was it run on (CPU, memory, compiler options, single user/multi-user, peripherals, network); how does the benchmark relate to your workload?

Well-known benchmarks include Whetstone, Dhrystone, Rhealstone (see h), the Gabriel benchmarks for Lisp, the SPECmark suite, and LINPACK.

See also machoflops, MIPS, smoke and mirrors.

Usenet newsgroup: news:comp.benchmarks.

Tennessee BenchWeb.


A performance test of hardware and/or software. There are various programs that very accurately test the raw power of a single machine, the interaction in a single client/server system (one server/multiple clients) and the transactions per second in a transaction processing system. However, it is next to impossible to benchmark the performance of an entire enterprise network with a great degree of accuracy.

Benchmarks may change their rating scale with new releases of the software. Thus, the same version of the test must often be run to compare results. See PC Magazine benchmarks, BAPCo, ECperf, Linpack, Dhrystone, Whetstone, Khornerstone, SPEC, GPC and RAMP-C.
References in periodicals archive ?
In the two-tier SAP Standard Application mySAP(tm) Utilities-Customer Care and Service (I-SU/CCS) Benchmark, it achieved 108,551 Utility Reference Customers per hour for its 16-way system (5)
This body of data pointed to the need for a small set of benchmarks that could in fact satisfy end-users' requirements, as outlined in the mission detailed for the SPC.
It is apparent from these graphs that managing life insurance company assets and the development of an effective performance benchmark cannot be separated from the management of the liability portfolio.
All of the hard work now will pay off because the right benchmark can help eliminate the window dressing some fund managers present to investors.
You choose the second option, a press coverage benchmark, assuming that the press reflects what's going on in the marketplace.
Logical volumes used to store data in SPC-1 must demonstrate the ability to preserve data across extended periods of power loss without corruption or loss to ensure the benchmark configuration provides enterprise class reliability in the presence of 1/O load.
The SPC has developed a rich infrastructure to ensure that benchmark results will be easily produced and that the results will be credible and widely disseminated.
The BDTI Benchmark suite is a unique, vendor-independent tool that enables meaningful comparisons between processors used in digital signal processing applications.
The Council's first benchmark (SPC-1) is designed to have broad market appeal and provide a level playing field between "open" providers of storage (either direct attach or storage networks).