{"id":6104,"date":"2026-10-19T16:48:50","date_gmt":"2026-10-19T16:48:50","guid":{"rendered":"https:\/\/i10xnews.kinsta.cloud\/?p=6104"},"modified":"2026-10-19T17:15:19","modified_gmt":"2026-10-19T17:15:19","slug":"agents-last-exam-hard-workflows-benchmark","status":"publish","type":"post","link":"https:\/\/i10x.ai\/news\/agents-last-exam-hard-workflows-benchmark","title":{"rendered":"Agents&#8217; Last Exam: Even Top Coding Agents Score Under 10% on the Hardest Tier"},"content":{"rendered":"\n<h2 class=\"wp-block-heading\">\u26a1 Quick Take<\/h2>\n\n<ul class=\"wp-block-list\"><li><strong>The finding:<\/strong> Codex with GPT-5.5, which scores 82% on Terminal-Bench, reaches only 23.3% overall on ALE-CLI and 0.0% on the hardest Last-Exam tier.<\/li><li><strong>Still unsaturated:<\/strong> Across mainstream harness and backbone setups, average full pass rate is below 1% on the hardest tier; most agents including Claude Code are near zero there.<\/li><li><strong>What it means:<\/strong> Short coding-agent benchmarks are saturating. Long expert workflows are not.<\/li><\/ul>\n\n\n<p class=\"wp-block-paragraph\">Coding agents look strong on Terminal-Bench and similar suites. Agents&#8217; Last Exam (ALE) asks a harder question: can they complete long, expert-authored professional workflows that take hours? A large consortium spanning universities and industry released ALE with 1,490 task instances across domains, keeping most of them private to limit overfitting.<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1344\" height=\"768\" src=\"https:\/\/i10xnews.kinsta.cloud\/wp-content\/uploads\/2026\/10\/agents-last-exam-hard-workflows-benchmark-pass-rates.webp\" alt=\"Column chart: Codex with GPT-5.5 scores 82 percent on Terminal-Bench, 37.2 on ALE Near-Term, 23.3 overall on ALE-CLI and 0 on Last-Exam.\" class=\"wp-image-6103\" srcset=\"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/agents-last-exam-hard-workflows-benchmark-pass-rates.webp 1344w, https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/agents-last-exam-hard-workflows-benchmark-pass-rates-300x171.webp 300w, https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/agents-last-exam-hard-workflows-benchmark-pass-rates-1024x585.webp 1024w, https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/agents-last-exam-hard-workflows-benchmark-pass-rates-768x439.webp 768w\" sizes=\"auto, (max-width: 1344px) 100vw, 1344px\" \/><figcaption class=\"wp-element-caption\">i10X chart based on data from Sun et al. (2026), arXiv:2606.05405, ALE-CLI results vs Terminal-Bench comparison (CC BY 4.0).<\/figcaption><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\">\ud83d\udd2c What the study shows<\/h2>\n\n\n<p class=\"wp-block-paragraph\">Only about 150 of 1,490 instances (~10%) are public; the rest stay in a private pool. Tasks are split into Near-Term (67 workflows where top pass rates approach 40%), Full-Spectrum and Last-Exam (38 hardest workflows). Each run is capped at five hours.<\/p>\n\n\n\n<figure class=\"wp-block-table\"><table><thead><tr><th>Configuration \/ tier<\/th><th>Pass rate<\/th><\/tr><\/thead><tbody><tr><td>Codex + GPT-5.5 on Terminal-Bench (reported)<\/td><td>82%<\/td><\/tr><tr><td>Same setup, ALE-CLI overall<\/td><td>23.3%<\/td><\/tr><tr><td>Same, Near-Term<\/td><td>37.2%<\/td><\/tr><tr><td>Same, Full-Spectrum<\/td><td>19.0%<\/td><\/tr><tr><td>Same, Last-Exam<\/td><td>0.0%<\/td><\/tr><tr><td>Average full pass, hardest tier (mainstream)<\/td><td>below 1%<\/td><\/tr><\/tbody><\/table><figcaption class=\"wp-element-caption\">Headline comparisons as reported in the paper.<\/figcaption><\/figure>\n\n\n<ul class=\"wp-block-list\"><li><strong>Costly to run:<\/strong> A single frontier-agent run on one ALE task costs about $3\u201310 and takes tens of minutes to hours.<\/li><li><strong>Timeouts are real:<\/strong> Overall timeout rate is 3.8%, from ~1% for lightweight harnesses to 5.7% for OpenClaw.<\/li><li><strong>Failure modes vary:<\/strong> Analyses show incomplete implementations, domain-knowledge gaps, hallucinations and tool-use errors across configs.<\/li><\/ul>\n\n\n<h2 class=\"wp-block-heading\">\u2705 Why it matters: headroom returns<\/h2>\n\n\n<p class=\"wp-block-paragraph\">When agents score 70\u201380% on popular coding benches, it is easy to declare the problem solved. ALE shows that economically valuable, multi-hour workflows remain almost untouched.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The private holdout is an explicit response to contamination of public agent tests.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\ud83e\uddea Method in brief<\/h2>\n\n\n<p class=\"wp-block-paragraph\">Expert-contributed workflows with a public\/private split, multi-tier difficulty, five-hour caps and a living leaderboard. Project site and Hugging Face assets accompany the paper.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\u2753 What remains open<\/h2>\n\n<ul class=\"wp-block-list\"><li><strong>Expensive evaluation:<\/strong> $3\u201310 per task limits who can iterate quickly.<\/li><li><strong>Moving target:<\/strong> Harnesses and backbones change; leaderboard numbers will drift.<\/li><\/ul>\n\n\n<h2 class=\"wp-block-heading\">\ud83e\udded Context<\/h2>\n\n\n<p class=\"wp-block-paragraph\">ALE sits above short CLI and GUI agent benches. More agent evaluation is in <a href=\"\/news\/category\/studies\/benchmarks-evals\">Benchmarks &amp; Evals<\/a> and <a href=\"\/news\/category\/studies\/agent-research\">Agents<\/a>.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\ud83d\udee0\ufe0f What it means for agent builders<\/h2>\n\n<ul class=\"wp-block-list\"><li><strong>Stop optimizing only Terminal-Bench:<\/strong> Add long workflow evaluations.<\/li><li><strong>Budget for hours, not minutes:<\/strong> Timeouts and cost are part of the product.<\/li><li><strong>Use the private split:<\/strong> Treat public ALE tasks as practice, not the score that matters.<\/li><\/ul>\n\n\n<h2 class=\"wp-block-heading\">\u270d\ufe0f About the analysis<\/h2>\n\n\n<p class=\"wp-block-paragraph\">This article is based on the full text of the preprint &#8220;Agents&#x27; Last Exam&#8221; (arXiv:2606.05405v3, submitted June 3, 2026). All numbers are taken from the paper&#8217;s text, tables and figures; i10X did not rerun the experiments. The chart was redrawn by i10X from ALE-CLI results vs Terminal-Bench comparison of the paper, which is published under a CC BY 4.0 license.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\ud83d\udd2d i10x Perspective<\/h2>\n\n\n<p class=\"wp-block-paragraph\">ALE&#8217;s zero on the hardest tier for a model that dominates Terminal-Bench is the kind of result the field needs: proof that agent capability is still narrowly concentrated. The private pool is almost as important as the tasks. Without it, tomorrow&#8217;s agents would memorize today&#8217;s expert workflows.<\/p>\n\n","protected":false},"excerpt":{"rendered":"<p>ALE holds 1,490 expert workflows; the best Codex+GPT-5.5 setup that scores 82% on Terminal-Bench gets under 10% on ALE&#8217;s hardest tier and 23.3% overall on ALE-CLI.<\/p>\n","protected":false},"author":2,"featured_media":6254,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"paper_title":"Agents' Last Exam","paper_url":"https:\/\/arxiv.org\/abs\/2606.05405","pdf_url":"https:\/\/arxiv.org\/pdf\/2606.05405v3","doi":"","arxiv_id":"2606.05405","authors":"Yiyou Sun, Xinyang Han, Weichen Zhang, Xiang Liu, Yuanbo Pang, Tianyu Wang, Yuhan Cao, Yixiao Huang, Zhaowei Zhang, Chris Duroiu, Haoyun Zhang, Jeffrey Lin et al. (357 authors)","institutions":"Multi-institution consortium (core contributors listed; advisory committee across universities)","paper_date":"2026-06-03","venue":"arXiv (cs.AI), version 3","peer_reviewed":false,"code_url":"","data_url":"","funding_coi":"Large multi-affiliation project; see paper for full contributor list.","figure_license":"Chart drawn by i10X from ALE-CLI results vs Terminal-Bench comparison (CC BY 4.0)","paper_license":"CC BY 4.0","replication":"no","study_models":"Multiple agent harnesses and backbones incl. Codex+GPT-5.5, Claude Code, OpenClaw and others","study_sample":"1,490 workflow instances; ~150 public; Near-Term\/Full-Spectrum\/Last-Exam tiers","footnotes":"","_yoast_wpseo_primary_category":""},"categories":[53,52],"tags":[],"companies":[39,38],"products":[],"class_list":["post-6104","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-benchmarks-evals","category-studies","company-anthropic","company-open-ai"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.7 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Agents&#039; Last Exam: Hard Professional Workflows Still Unsolved - i10X News<\/title>\n<meta name=\"description\" content=\"ALE benchmark: top agents that ace Terminal-Bench score under 10% on the hardest tier. 1,490 expert workflows, private holdout.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/i10x.ai\/news\/agents-last-exam-hard-workflows-benchmark\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Agents&#039; Last Exam: Hard Professional Workflows Still Unsolved - i10X News\" \/>\n<meta property=\"og:description\" content=\"ALE benchmark: top agents that ace Terminal-Bench score under 10% on the hardest tier. 1,490 expert workflows, private holdout.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/i10x.ai\/news\/agents-last-exam-hard-workflows-benchmark\" \/>\n<meta property=\"og:site_name\" content=\"i10X News\" \/>\n<meta property=\"article:published_time\" content=\"2026-10-19T16:48:50+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-10-19T17:15:19+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/agents-last-exam-hard-workflows-benchmark-title.webp\" \/>\n\t<meta property=\"og:image:width\" content=\"1344\" \/>\n\t<meta property=\"og:image:height\" content=\"768\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/webp\" \/>\n<meta name=\"author\" content=\"Christopher Ort\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@i10x_ai\" \/>\n<meta name=\"twitter:site\" content=\"@i10x_ai\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Christopher Ort\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/agents-last-exam-hard-workflows-benchmark#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/agents-last-exam-hard-workflows-benchmark\"},\"author\":{\"name\":\"Christopher Ort\",\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#\\\/schema\\\/person\\\/d410bb7ee72febefca2c9c369939219a\"},\"headline\":\"Agents&#8217; Last Exam: Even Top Coding Agents Score Under 10% on the Hardest Tier\",\"datePublished\":\"2026-10-19T16:48:50+00:00\",\"dateModified\":\"2026-10-19T17:15:19+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/agents-last-exam-hard-workflows-benchmark\"},\"wordCount\":536,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/agents-last-exam-hard-workflows-benchmark#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/agents-last-exam-hard-workflows-benchmark-title.webp\",\"articleSection\":[\"Benchmarks &amp; Evals\",\"Studies\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/i10x.ai\\\/news\\\/agents-last-exam-hard-workflows-benchmark#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/agents-last-exam-hard-workflows-benchmark\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\\\/agents-last-exam-hard-workflows-benchmark\",\"name\":\"Agents' Last Exam: Hard Professional Workflows Still Unsolved - i10X News\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/agents-last-exam-hard-workflows-benchmark#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/agents-last-exam-hard-workflows-benchmark#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/agents-last-exam-hard-workflows-benchmark-title.webp\",\"datePublished\":\"2026-10-19T16:48:50+00:00\",\"dateModified\":\"2026-10-19T17:15:19+00:00\",\"description\":\"ALE benchmark: top agents that ace Terminal-Bench score under 10% on the hardest tier. 1,490 expert workflows, private holdout.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/agents-last-exam-hard-workflows-benchmark#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/i10x.ai\\\/news\\\/agents-last-exam-hard-workflows-benchmark\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/agents-last-exam-hard-workflows-benchmark#primaryimage\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/agents-last-exam-hard-workflows-benchmark-title.webp\",\"contentUrl\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/agents-last-exam-hard-workflows-benchmark-title.webp\",\"width\":1344,\"height\":768,\"caption\":\"Illustration: i10X\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/agents-last-exam-hard-workflows-benchmark#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/news.i10x.ai\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Agents&#8217; Last Exam: Even Top Coding Agents Score Under 10% on the Hardest Tier\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#website\",\"url\":\"https:\\\/\\\/news.i10x.ai\\\/\",\"name\":\"i10X News\",\"description\":\"Stay updated with the latest news and announcements from i10X.\",\"publisher\":{\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/news.i10x.ai\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#organization\",\"name\":\"i10X\",\"url\":\"https:\\\/\\\/news.i10x.ai\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/i10x-logo-180.png\",\"contentUrl\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/i10x-logo-180.png\",\"width\":180,\"height\":180,\"caption\":\"i10X\"},\"image\":{\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/x.com\\\/i10x_ai\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/i10x-ai\",\"https:\\\/\\\/instagram.com\\\/i10x.ai\",\"https:\\\/\\\/www.youtube.com\\\/@i10X_ai_official\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#\\\/schema\\\/person\\\/d410bb7ee72febefca2c9c369939219a\",\"name\":\"Christopher Ort\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/christopher-ort-192.webp\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/christopher-ort-192.webp\",\"contentUrl\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/christopher-ort-192.webp\",\"caption\":\"Christopher Ort\"},\"description\":\"Christopher Ort handles SEO, AI agent workflows and PR & partnerships at i10x.ai, the all-in-one AI workspace built by i10X Global Pte. Ltd. in Singapore. He is a graduate of Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU). He is the author of \u201cThe Style Penalty\u201d, a study published on SSRN that analyses 1,576 evaluation decisions by four frontier AI models to show how AI-written CVs fare in automated hiring screens; the research has been covered by heise online and t3n.\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\\\/author\\\/christopher-ort\",\"sameAs\":[\"https:\\\/\\\/i10x.ai\\\/blog\\\/author\\\/christopher-ort\"],\"worksFor\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#organization\"},\"alumniOf\":{\"@type\":\"EducationalOrganization\",\"name\":\"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU)\",\"url\":\"https:\\\/\\\/www.fau.eu\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Agents' Last Exam: Hard Professional Workflows Still Unsolved - i10X News","description":"ALE benchmark: top agents that ace Terminal-Bench score under 10% on the hardest tier. 1,490 expert workflows, private holdout.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/i10x.ai\/news\/agents-last-exam-hard-workflows-benchmark","og_locale":"en_US","og_type":"article","og_title":"Agents' Last Exam: Hard Professional Workflows Still Unsolved - i10X News","og_description":"ALE benchmark: top agents that ace Terminal-Bench score under 10% on the hardest tier. 1,490 expert workflows, private holdout.","og_url":"https:\/\/i10x.ai\/news\/agents-last-exam-hard-workflows-benchmark","og_site_name":"i10X News","article_published_time":"2026-10-19T16:48:50+00:00","article_modified_time":"2026-10-19T17:15:19+00:00","og_image":[{"width":1344,"height":768,"url":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/agents-last-exam-hard-workflows-benchmark-title.webp","type":"image\/webp"}],"author":"Christopher Ort","twitter_card":"summary_large_image","twitter_creator":"@i10x_ai","twitter_site":"@i10x_ai","twitter_misc":{"Written by":"Christopher Ort","Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/i10x.ai\/news\/agents-last-exam-hard-workflows-benchmark#article","isPartOf":{"@id":"https:\/\/i10x.ai\/news\/agents-last-exam-hard-workflows-benchmark"},"author":{"name":"Christopher Ort","@id":"https:\/\/news.i10x.ai\/#\/schema\/person\/d410bb7ee72febefca2c9c369939219a"},"headline":"Agents&#8217; Last Exam: Even Top Coding Agents Score Under 10% on the Hardest Tier","datePublished":"2026-10-19T16:48:50+00:00","dateModified":"2026-10-19T17:15:19+00:00","mainEntityOfPage":{"@id":"https:\/\/i10x.ai\/news\/agents-last-exam-hard-workflows-benchmark"},"wordCount":536,"commentCount":0,"publisher":{"@id":"https:\/\/news.i10x.ai\/#organization"},"image":{"@id":"https:\/\/i10x.ai\/news\/agents-last-exam-hard-workflows-benchmark#primaryimage"},"thumbnailUrl":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/agents-last-exam-hard-workflows-benchmark-title.webp","articleSection":["Benchmarks &amp; Evals","Studies"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/i10x.ai\/news\/agents-last-exam-hard-workflows-benchmark#respond"]}]},{"@type":"WebPage","@id":"https:\/\/i10x.ai\/news\/agents-last-exam-hard-workflows-benchmark","url":"https:\/\/i10x.ai\/news\/agents-last-exam-hard-workflows-benchmark","name":"Agents' Last Exam: Hard Professional Workflows Still Unsolved - i10X News","isPartOf":{"@id":"https:\/\/news.i10x.ai\/#website"},"primaryImageOfPage":{"@id":"https:\/\/i10x.ai\/news\/agents-last-exam-hard-workflows-benchmark#primaryimage"},"image":{"@id":"https:\/\/i10x.ai\/news\/agents-last-exam-hard-workflows-benchmark#primaryimage"},"thumbnailUrl":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/agents-last-exam-hard-workflows-benchmark-title.webp","datePublished":"2026-10-19T16:48:50+00:00","dateModified":"2026-10-19T17:15:19+00:00","description":"ALE benchmark: top agents that ace Terminal-Bench score under 10% on the hardest tier. 1,490 expert workflows, private holdout.","breadcrumb":{"@id":"https:\/\/i10x.ai\/news\/agents-last-exam-hard-workflows-benchmark#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/i10x.ai\/news\/agents-last-exam-hard-workflows-benchmark"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/i10x.ai\/news\/agents-last-exam-hard-workflows-benchmark#primaryimage","url":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/agents-last-exam-hard-workflows-benchmark-title.webp","contentUrl":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/agents-last-exam-hard-workflows-benchmark-title.webp","width":1344,"height":768,"caption":"Illustration: i10X"},{"@type":"BreadcrumbList","@id":"https:\/\/i10x.ai\/news\/agents-last-exam-hard-workflows-benchmark#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/news.i10x.ai\/"},{"@type":"ListItem","position":2,"name":"Agents&#8217; Last Exam: Even Top Coding Agents Score Under 10% on the Hardest Tier"}]},{"@type":"WebSite","@id":"https:\/\/news.i10x.ai\/#website","url":"https:\/\/news.i10x.ai\/","name":"i10X News","description":"Stay updated with the latest news and announcements from i10X.","publisher":{"@id":"https:\/\/news.i10x.ai\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/news.i10x.ai\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/news.i10x.ai\/#organization","name":"i10X","url":"https:\/\/news.i10x.ai\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/news.i10x.ai\/#\/schema\/logo\/image\/","url":"https:\/\/i10xnews.kinsta.cloud\/wp-content\/uploads\/2026\/10\/i10x-logo-180.png","contentUrl":"https:\/\/i10xnews.kinsta.cloud\/wp-content\/uploads\/2026\/10\/i10x-logo-180.png","width":180,"height":180,"caption":"i10X"},"image":{"@id":"https:\/\/news.i10x.ai\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/i10x_ai","https:\/\/www.linkedin.com\/company\/i10x-ai","https:\/\/instagram.com\/i10x.ai","https:\/\/www.youtube.com\/@i10X_ai_official"]},{"@type":"Person","@id":"https:\/\/news.i10x.ai\/#\/schema\/person\/d410bb7ee72febefca2c9c369939219a","name":"Christopher Ort","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/christopher-ort-192.webp","url":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/christopher-ort-192.webp","contentUrl":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/christopher-ort-192.webp","caption":"Christopher Ort"},"description":"Christopher Ort handles SEO, AI agent workflows and PR & partnerships at i10x.ai, the all-in-one AI workspace built by i10X Global Pte. Ltd. in Singapore. He is a graduate of Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU). He is the author of \u201cThe Style Penalty\u201d, a study published on SSRN that analyses 1,576 evaluation decisions by four frontier AI models to show how AI-written CVs fare in automated hiring screens; the research has been covered by heise online and t3n.","url":"https:\/\/i10x.ai\/news\/author\/christopher-ort","sameAs":["https:\/\/i10x.ai\/blog\/author\/christopher-ort"],"worksFor":{"@id":"https:\/\/i10x.ai\/news\/#organization"},"alumniOf":{"@type":"EducationalOrganization","name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU)","url":"https:\/\/www.fau.eu"}}]}},"_links":{"self":[{"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/posts\/6104","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/comments?post=6104"}],"version-history":[{"count":2,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/posts\/6104\/revisions"}],"predecessor-version":[{"id":6255,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/posts\/6104\/revisions\/6255"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/media\/6254"}],"wp:attachment":[{"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/media?parent=6104"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/categories?post=6104"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/tags?post=6104"},{"taxonomy":"company","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/companies?post=6104"},{"taxonomy":"product","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/products?post=6104"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}