{"id":2582,"date":"2025-09-29T12:25:39","date_gmt":"2025-09-29T16:25:39","guid":{"rendered":"https:\/\/blog.richmond.edu\/writing\/?p=2582"},"modified":"2025-09-29T12:28:11","modified_gmt":"2025-09-29T16:28:11","slug":"word-of-the-week-benchmark","status":"publish","type":"post","link":"https:\/\/blog.richmond.edu\/writing\/2025\/09\/29\/word-of-the-week-benchmark\/","title":{"rendered":"Word of the Week! Benchmark"},"content":{"rendered":"<p><a href=\"http:\/\/blog.richmond.edu\/writing\/files\/2025\/09\/benchmark.jpg\"><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter wp-image-2583\" src=\"http:\/\/blog.richmond.edu\/writing\/files\/2025\/09\/benchmark-205x300.jpg\" alt=\"Surveyors at archaeological site in England\" width=\"306\" height=\"448\" srcset=\"https:\/\/blog.richmond.edu\/writing\/files\/2025\/09\/benchmark-205x300.jpg 205w, https:\/\/blog.richmond.edu\/writing\/files\/2025\/09\/benchmark.jpg 547w\" sizes=\"auto, (max-width: 306px) 100vw, 306px\" \/><\/a>In my course &#8220;Writing With And About AI&#8221; my students have been discussing benchmark testing for large language models and how companies might be &#8220;cheating on the tests&#8221; by pre-loading the test questions into their AIs. That phenomenon is called &#8220;benchmark contamination.&#8221;<\/p>\n<p>If proven true for major firms that provide popular models such as Anthropic, Google, or OpenAI, it portends that progress in AI &#8220;intelligence&#8221; may be greatly exaggerated by those firms as they seek customers and investment capital.<\/p>\n<p>This blog is not about AI per se, but the use of &#8220;benchmark&#8221; got me thinking of my drill press and shop bench on the farm. Careful measurements matter, so where exactly did &#8220;benchmark&#8221; come from?<\/p>\n<p>Not the shop bench, as I haphazardly guessed in class. Instead, <a href=\"https:\/\/www.oed.com\/dictionary\/benchmark_n?tab=meaning_and_use#23626762\" target=\"_blank\" rel=\"noopener\">the OED entry<\/a> notes that for surveyors&#8217; tools, such &#8220;a mark takes the form of a horizontal groove cut in a surface, into which the upper surface of an angle iron would once have been inserted, forming a level surface or \u2018bench\u2019 to support a levelling staff.&#8221;\u00a0 If you have had the pleasure of looking at the high level of detail on British <a href=\"https:\/\/www.ordnancesurvey.co.uk\/\" target=\"_blank\" rel=\"noopener\">Ordinance Survey Maps<\/a>, you will quickly grasp how important a good benchmark proves for careful measurements.\u00a0 First usage recorded is 1826 from the US, during the surveying for the <a href=\"https:\/\/www.nps.gov\/choh\/index.htm\" target=\"_blank\" rel=\"noopener\">Ohio and Chesapeake Canal<\/a>, and the etymology remains a simple compound of two common English words.<\/p>\n<p>You may use our word as noun or verb without attracting the fury of grammatical purists. If you do, just tell them &#8220;benchmark that!&#8221; and wave an angle iron at them.<\/p>\n<p>Send words and metaphors my way by e-mailing me (jessid -at- richmond -dot- edu) or leaving a comment below. Want to write a guest entry? Let me know!<\/p>\n<p>See all of our Metaphors of the Month\u00a0<a href=\"https:\/\/blog.richmond.edu\/writing\/tag\/metaphor-of-the-month\/\" target=\"_blank\" rel=\"noopener noreferrer\">here<\/a>\u00a0and Words of the Week\u00a0<a href=\"https:\/\/blog.richmond.edu\/writing\/tag\/word-of-the-week\/\">here<\/a>.<\/p>\n<p><em>Image: &#8220;Mapping a feature&#8221; from <a href=\"https:\/\/www.flickr.com\/photos\/wessexarchaeology\/176339319\/\" target=\"_blank\" rel=\"noopener\">Wessex Archaeology<\/a>, via Flickr<\/em><\/p>\n","protected":false},"excerpt":{"rendered":"<p>In my course &#8220;Writing With And About AI&#8221; my students have been discussing benchmark testing for large language models and how companies might be &#8220;cheating on the tests&#8221; by pre-loading the test questions into their AIs. That phenomenon is called &#8220;benchmark contamination.&#8221; If proven true for major firms that provide popular models such as Anthropic, &hellip; <a href=\"https:\/\/blog.richmond.edu\/writing\/2025\/09\/29\/word-of-the-week-benchmark\/\" class=\"more-link\">Continue reading <span class=\"screen-reader-text\">Word of the Week! Benchmark<\/span><\/a><\/p>\n","protected":false},"author":589,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"jetpack_post_was_ever_published":false,"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[2516,87405,1027,40197,99],"tags":[2522],"class_list":["post-2582","post","type-post","status-publish","format-standard","hentry","category-academic-writing","category-etymology","category-technoculture","category-vocabulary","category-writing","tag-word-of-the-week"],"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"jetpack_shortlink":"https:\/\/wp.me\/pcsCNV-FE","_links":{"self":[{"href":"https:\/\/blog.richmond.edu\/writing\/wp-json\/wp\/v2\/posts\/2582","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blog.richmond.edu\/writing\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blog.richmond.edu\/writing\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blog.richmond.edu\/writing\/wp-json\/wp\/v2\/users\/589"}],"replies":[{"embeddable":true,"href":"https:\/\/blog.richmond.edu\/writing\/wp-json\/wp\/v2\/comments?post=2582"}],"version-history":[{"count":3,"href":"https:\/\/blog.richmond.edu\/writing\/wp-json\/wp\/v2\/posts\/2582\/revisions"}],"predecessor-version":[{"id":2586,"href":"https:\/\/blog.richmond.edu\/writing\/wp-json\/wp\/v2\/posts\/2582\/revisions\/2586"}],"wp:attachment":[{"href":"https:\/\/blog.richmond.edu\/writing\/wp-json\/wp\/v2\/media?parent=2582"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blog.richmond.edu\/writing\/wp-json\/wp\/v2\/categories?post=2582"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blog.richmond.edu\/writing\/wp-json\/wp\/v2\/tags?post=2582"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}