{"id":6116,"date":"2026-10-19T16:48:59","date_gmt":"2026-10-19T16:48:59","guid":{"rendered":"https:\/\/i10xnews.kinsta.cloud\/?p=6116"},"modified":"2026-10-19T17:17:05","modified_gmt":"2026-10-19T17:17:05","slug":"weavebench-hybrid-gui-cli-computer-use","status":"publish","type":"post","link":"https:\/\/i10x.ai\/news\/weavebench-hybrid-gui-cli-computer-use","title":{"rendered":"Hybrid Computer-Use Agents Top Out at 41% When GUI and CLI Must Work Together"},"content":{"rendered":"\n<h2 class=\"wp-block-heading\">\u26a1 Quick Take<\/h2>\n\n<ul class=\"wp-block-list\"><li><strong>The finding:<\/strong> Across frontier model\u2013runtime pairings, the best WeaveBench PassRate is 41.2% (Claude Opus 4.7 + Claude Code).<\/li><li><strong>Interfaces must combine:<\/strong> GUI-only stays \u22641.8% and CLI-only \u22643.5% \u2014 an order of magnitude below hybrid.<\/li><li><strong>Judges matter:<\/strong> A trajectory-aware judge cuts GPT-5.5 from an outcome-only 53.5% to an audited 33.3%, catching fabricated evidence and shortcuts.<\/li><\/ul>\n\n\n<p class=\"wp-block-paragraph\">Computer-use agents increasingly mix desktop GUI control, CLI, code editors, browsers and tools. Microsoft Research Asia and Tsinghua researchers argue that most benches still treat those interfaces as separable. WeaveBench forces them into one long-horizon trajectory.<\/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\/weavebench-hybrid-gui-cli-computer-use-interfaces.webp\" alt=\"Column chart: GUI-only at most 1.8 percent, CLI-only 3.5, best hybrid pairing 41.2 percent.\" class=\"wp-image-6115\" srcset=\"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/weavebench-hybrid-gui-cli-computer-use-interfaces.webp 1344w, https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/weavebench-hybrid-gui-cli-computer-use-interfaces-300x171.webp 300w, https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/weavebench-hybrid-gui-cli-computer-use-interfaces-1024x585.webp 1024w, https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/weavebench-hybrid-gui-cli-computer-use-interfaces-768x439.webp 768w\" sizes=\"auto, (max-width: 1344px) 100vw, 1344px\" \/><figcaption class=\"wp-element-caption\">i10X chart based on data from Li et al. (2026), arXiv:2606.09426, interface ablation and best pairing (arXiv non-exclusive license).<\/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\">114 tasks across 8 real-world work domains, grounded in real user requests with publicly verifiable artifacts, run on a real Ubuntu desktop inside deployed CLI-agent runtimes plus a desktop-control plugin.<\/p>\n\n\n<ul class=\"wp-block-list\"><li><strong>Far below OSWorld:<\/strong> Same-class backbones exceed 78% on OSWorld-Verified but stay in the 30s\u201340s here.<\/li><li><strong>Runtime pairing matters:<\/strong> Claude Opus 4.7 falls from 41.2% on Claude Code to 13.2% on Codex CLI; GPT-5.5 drops from 35.1% to 14.9% on Claude Code.<\/li><li><strong>Within-series spread:<\/strong> GPT-5.1-codex scores 1.8% vs GPT-5.5 at 33.3% on the fixed OpenClaw harness.<\/li><\/ul>\n\n\n<h2 class=\"wp-block-heading\">\u2705 Why it matters: real work is hybrid<\/h2>\n\n\n<p class=\"wp-block-paragraph\">Knowledge workers do not stay in one surface. Agents that can only click or only shell will fail the jobs people actually assign.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\ud83e\uddea Method in brief<\/h2>\n\n\n<p class=\"wp-block-paragraph\">Trajectory-aware judge inspects deliverables, files, screenshots, logs and action traces for shortcuts. Project: weavebench.github.io.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\u2753 What remains open<\/h2>\n\n<ul class=\"wp-block-list\"><li><strong>Ubuntu desktop scope:<\/strong> Other OSes untested.<\/li><li><strong>Plugin-augmented runtimes:<\/strong> Results depend on the desktop-control bridge.<\/li><\/ul>\n\n\n<h2 class=\"wp-block-heading\">\ud83e\udded Context<\/h2>\n\n\n<p class=\"wp-block-paragraph\">Related GUI\/CUA work is in <a href=\"\/news\/category\/studies\/benchmarks-evals\">Benchmarks &amp; Evals<\/a>.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\ud83d\udee0\ufe0f What it means for CUA products<\/h2>\n\n<ul class=\"wp-block-list\"><li><strong>Ship hybrid by default:<\/strong> Single-channel modes fail these tasks.<\/li><li><strong>Audit trajectories:<\/strong> Outcome-only scores inflate success.<\/li><li><strong>Match model to runtime:<\/strong> Cross-pairings collapse scores.<\/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;WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces&#8221; (arXiv:2606.09426v3, submitted June 8, 2026). All numbers are taken from the paper&#8217;s text, tables and figures; i10X did not rerun the experiments. The paper is distributed under arXiv&#8217;s non-exclusive license, so i10X does not reproduce its figures; the chart was drawn by i10X from numbers reported in interface ablation and best pairing.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\ud83d\udd2d i10x Perspective<\/h2>\n\n\n<p class=\"wp-block-paragraph\">WeaveBench&#8217;s sharpest result is the ablation: strip away either GUI or CLI and PassRate collapses to a few percent. The hybrid agent is not a convenience feature. It is the capability.<\/p>\n\n","protected":false},"excerpt":{"rendered":"<p>WeaveBench&#8217;s 114 real-world tasks: best PassRate 41.2%. GUI-only or CLI-only collapse below 3.5%. Outcome-only grading overestimates GPT-5.5 from 53.5% to an audited 33.3%.<\/p>\n","protected":false},"author":2,"featured_media":6266,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"paper_title":"WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces","paper_url":"https:\/\/arxiv.org\/abs\/2606.09426","pdf_url":"https:\/\/arxiv.org\/pdf\/2606.09426v3","doi":"","arxiv_id":"2606.09426","authors":"Wanli Li, Bowen Zhou, Yunyao Yu, Zhou Xu, Yifan Yang, Dongsheng Li, Caihua Shan","institutions":"Microsoft Research Asia; Tsinghua University","paper_date":"2026-06-08","venue":"arXiv (cs.AI), version 3","peer_reviewed":false,"code_url":"","data_url":"","funding_coi":"Microsoft Research Asia corresponding author.","figure_license":"Chart drawn by i10X from interface ablation and best pairing (arXiv non-exclusive license)","paper_license":"arXiv non-exclusive license","replication":"no","study_models":"Frontier CUAs incl. Claude Opus 4.7, GPT-5.5\/5.4 across OpenClaw, Claude Code, Codex CLI","study_sample":"114 hybrid-interface tasks across 8 domains","footnotes":"","_yoast_wpseo_primary_category":""},"categories":[53,52],"tags":[],"companies":[39,43,38],"products":[51],"class_list":["post-6116","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-benchmarks-evals","category-studies","company-anthropic","company-microsoft","company-open-ai","product-claude"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.7 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>WeaveBench: Hybrid GUI+CLI Computer-Use Is Still Hard - i10X News<\/title>\n<meta name=\"description\" content=\"WeaveBench: 114 hybrid-interface tasks, best PassRate 41.2%. Single-interface modes fail; trajectory judges cut inflated scores.\" \/>\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\/weavebench-hybrid-gui-cli-computer-use\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"WeaveBench: Hybrid GUI+CLI Computer-Use Is Still Hard - i10X News\" \/>\n<meta property=\"og:description\" content=\"WeaveBench: 114 hybrid-interface tasks, best PassRate 41.2%. Single-interface modes fail; trajectory judges cut inflated scores.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/i10x.ai\/news\/weavebench-hybrid-gui-cli-computer-use\" \/>\n<meta property=\"og:site_name\" content=\"i10X News\" \/>\n<meta property=\"article:published_time\" content=\"2026-10-19T16:48:59+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-10-19T17:17:05+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/weavebench-hybrid-gui-cli-computer-use-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=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/weavebench-hybrid-gui-cli-computer-use#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/weavebench-hybrid-gui-cli-computer-use\"},\"author\":{\"name\":\"Christopher Ort\",\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#\\\/schema\\\/person\\\/d410bb7ee72febefca2c9c369939219a\"},\"headline\":\"Hybrid Computer-Use Agents Top Out at 41% When GUI and CLI Must Work Together\",\"datePublished\":\"2026-10-19T16:48:59+00:00\",\"dateModified\":\"2026-10-19T17:17:05+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/weavebench-hybrid-gui-cli-computer-use\"},\"wordCount\":418,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/weavebench-hybrid-gui-cli-computer-use#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/weavebench-hybrid-gui-cli-computer-use-title.webp\",\"articleSection\":[\"Benchmarks &amp; Evals\",\"Studies\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/i10x.ai\\\/news\\\/weavebench-hybrid-gui-cli-computer-use#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/weavebench-hybrid-gui-cli-computer-use\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\\\/weavebench-hybrid-gui-cli-computer-use\",\"name\":\"WeaveBench: Hybrid GUI+CLI Computer-Use Is Still Hard - i10X News\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/weavebench-hybrid-gui-cli-computer-use#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/weavebench-hybrid-gui-cli-computer-use#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/weavebench-hybrid-gui-cli-computer-use-title.webp\",\"datePublished\":\"2026-10-19T16:48:59+00:00\",\"dateModified\":\"2026-10-19T17:17:05+00:00\",\"description\":\"WeaveBench: 114 hybrid-interface tasks, best PassRate 41.2%. Single-interface modes fail; trajectory judges cut inflated scores.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/weavebench-hybrid-gui-cli-computer-use#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/i10x.ai\\\/news\\\/weavebench-hybrid-gui-cli-computer-use\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/weavebench-hybrid-gui-cli-computer-use#primaryimage\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/weavebench-hybrid-gui-cli-computer-use-title.webp\",\"contentUrl\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/weavebench-hybrid-gui-cli-computer-use-title.webp\",\"width\":1344,\"height\":768,\"caption\":\"Illustration: i10X\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/weavebench-hybrid-gui-cli-computer-use#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/news.i10x.ai\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Hybrid Computer-Use Agents Top Out at 41% When GUI and CLI Must Work Together\"}]},{\"@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":"WeaveBench: Hybrid GUI+CLI Computer-Use Is Still Hard - i10X News","description":"WeaveBench: 114 hybrid-interface tasks, best PassRate 41.2%. Single-interface modes fail; trajectory judges cut inflated scores.","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\/weavebench-hybrid-gui-cli-computer-use","og_locale":"en_US","og_type":"article","og_title":"WeaveBench: Hybrid GUI+CLI Computer-Use Is Still Hard - i10X News","og_description":"WeaveBench: 114 hybrid-interface tasks, best PassRate 41.2%. Single-interface modes fail; trajectory judges cut inflated scores.","og_url":"https:\/\/i10x.ai\/news\/weavebench-hybrid-gui-cli-computer-use","og_site_name":"i10X News","article_published_time":"2026-10-19T16:48:59+00:00","article_modified_time":"2026-10-19T17:17:05+00:00","og_image":[{"width":1344,"height":768,"url":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/weavebench-hybrid-gui-cli-computer-use-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":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/i10x.ai\/news\/weavebench-hybrid-gui-cli-computer-use#article","isPartOf":{"@id":"https:\/\/i10x.ai\/news\/weavebench-hybrid-gui-cli-computer-use"},"author":{"name":"Christopher Ort","@id":"https:\/\/news.i10x.ai\/#\/schema\/person\/d410bb7ee72febefca2c9c369939219a"},"headline":"Hybrid Computer-Use Agents Top Out at 41% When GUI and CLI Must Work Together","datePublished":"2026-10-19T16:48:59+00:00","dateModified":"2026-10-19T17:17:05+00:00","mainEntityOfPage":{"@id":"https:\/\/i10x.ai\/news\/weavebench-hybrid-gui-cli-computer-use"},"wordCount":418,"commentCount":0,"publisher":{"@id":"https:\/\/news.i10x.ai\/#organization"},"image":{"@id":"https:\/\/i10x.ai\/news\/weavebench-hybrid-gui-cli-computer-use#primaryimage"},"thumbnailUrl":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/weavebench-hybrid-gui-cli-computer-use-title.webp","articleSection":["Benchmarks &amp; Evals","Studies"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/i10x.ai\/news\/weavebench-hybrid-gui-cli-computer-use#respond"]}]},{"@type":"WebPage","@id":"https:\/\/i10x.ai\/news\/weavebench-hybrid-gui-cli-computer-use","url":"https:\/\/i10x.ai\/news\/weavebench-hybrid-gui-cli-computer-use","name":"WeaveBench: Hybrid GUI+CLI Computer-Use Is Still Hard - i10X News","isPartOf":{"@id":"https:\/\/news.i10x.ai\/#website"},"primaryImageOfPage":{"@id":"https:\/\/i10x.ai\/news\/weavebench-hybrid-gui-cli-computer-use#primaryimage"},"image":{"@id":"https:\/\/i10x.ai\/news\/weavebench-hybrid-gui-cli-computer-use#primaryimage"},"thumbnailUrl":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/weavebench-hybrid-gui-cli-computer-use-title.webp","datePublished":"2026-10-19T16:48:59+00:00","dateModified":"2026-10-19T17:17:05+00:00","description":"WeaveBench: 114 hybrid-interface tasks, best PassRate 41.2%. Single-interface modes fail; trajectory judges cut inflated scores.","breadcrumb":{"@id":"https:\/\/i10x.ai\/news\/weavebench-hybrid-gui-cli-computer-use#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/i10x.ai\/news\/weavebench-hybrid-gui-cli-computer-use"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/i10x.ai\/news\/weavebench-hybrid-gui-cli-computer-use#primaryimage","url":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/weavebench-hybrid-gui-cli-computer-use-title.webp","contentUrl":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/weavebench-hybrid-gui-cli-computer-use-title.webp","width":1344,"height":768,"caption":"Illustration: i10X"},{"@type":"BreadcrumbList","@id":"https:\/\/i10x.ai\/news\/weavebench-hybrid-gui-cli-computer-use#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/news.i10x.ai\/"},{"@type":"ListItem","position":2,"name":"Hybrid Computer-Use Agents Top Out at 41% When GUI and CLI Must Work Together"}]},{"@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\/6116","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=6116"}],"version-history":[{"count":2,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/posts\/6116\/revisions"}],"predecessor-version":[{"id":6267,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/posts\/6116\/revisions\/6267"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/media\/6266"}],"wp:attachment":[{"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/media?parent=6116"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/categories?post=6116"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/tags?post=6116"},{"taxonomy":"company","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/companies?post=6116"},{"taxonomy":"product","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/products?post=6116"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}