{"id":3855,"date":"2026-01-22T23:13:05","date_gmt":"2026-01-22T23:13:05","guid":{"rendered":"https:\/\/informedintel.com\/account\/datasecurity\/wp-datasecurity\/?p=3855"},"modified":"2026-01-22T23:13:05","modified_gmt":"2026-01-22T23:13:05","slug":"new-ai-benchmarks","status":"publish","type":"post","link":"https:\/\/informedintel.com\/account\/datasecurity\/wp-datasecurity\/new-ai-benchmarks\/","title":{"rendered":"New AI benchmarks"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\">New benchmark called\u00a0<a rel=\"noreferrer noopener\" href=\"https:\/\/arxiv.org\/abs\/2601.14242\" target=\"_blank\">APEX-Agents<\/a>\u00a0shows that every AI lab is failing in the workplace. \u201cFaced with queries from real professionals, even the best models struggled to get more than a quarter of the questions right. The vast majority of the time, the model came back with a wrong answer or no answer at all.\u201d<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/techcrunch.com\/2026\/01\/22\/are-ai-agents-ready-for-the-workplace-a-new-benchmark-raises-doubts\/\">TechCrunch | Are AI agents ready for the workplace? A new benchmark raises doubts.<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>New benchmark called\u00a0APEX-Agents\u00a0shows that every AI lab is failing in the workplace. \u201cFaced with queries from real professionals, even the best models struggled to get more than a quarter of the questions right. The vast majority of the time, the model came back with a wrong answer or no answer at all.\u201d TechCrunch | Are [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-3855","post","type-post","status-publish","format-standard","hentry","category-uncategorized","entry"],"_links":{"self":[{"href":"https:\/\/informedintel.com\/account\/datasecurity\/wp-datasecurity\/wp-json\/wp\/v2\/posts\/3855","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/informedintel.com\/account\/datasecurity\/wp-datasecurity\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/informedintel.com\/account\/datasecurity\/wp-datasecurity\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/informedintel.com\/account\/datasecurity\/wp-datasecurity\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/informedintel.com\/account\/datasecurity\/wp-datasecurity\/wp-json\/wp\/v2\/comments?post=3855"}],"version-history":[{"count":1,"href":"https:\/\/informedintel.com\/account\/datasecurity\/wp-datasecurity\/wp-json\/wp\/v2\/posts\/3855\/revisions"}],"predecessor-version":[{"id":3856,"href":"https:\/\/informedintel.com\/account\/datasecurity\/wp-datasecurity\/wp-json\/wp\/v2\/posts\/3855\/revisions\/3856"}],"wp:attachment":[{"href":"https:\/\/informedintel.com\/account\/datasecurity\/wp-datasecurity\/wp-json\/wp\/v2\/media?parent=3855"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/informedintel.com\/account\/datasecurity\/wp-datasecurity\/wp-json\/wp\/v2\/categories?post=3855"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/informedintel.com\/account\/datasecurity\/wp-datasecurity\/wp-json\/wp\/v2\/tags?post=3855"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}