[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-327140-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-327140-en":131},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","office-comprehension-benchmark-may-2026-abstract","Office Comprehension Benchmark - May 2026 - Abstract","","Office Comprehension Bench (OCB) is the first public benchmark that jointly evaluates LLM systems on Word, Excel, and PowerPoint comprehension using native file formats (.docx, .xlsx, .pptx) and variants. It provides two tracks: File Fidelity Q&A measuring structural and visual perception of office artifacts, and Domain Q&A testing multi-step expert reasoning across 12 professional domains. Responses are scored via atomic, binary-gradable claims and an ensemble of LLM judges, with results reported on a public leaderboard. Even frontier systems plateau around 59.3% in default reasoning mode, while deeper reasoning yields limited gains.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/office-comprehension-benchmark-may-2026-abstract/327140/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/office-comprehension-benchmark-may-2026-abstract/327140.png","ImageObject",300,407,{"name":42,"@type":43},"Lucas Martin","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-09","2026-09-21",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",26,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What does the Office Comprehension Bench (OCB) evaluate?","Question",{"text":63,"@type":64},"OCB evaluates LLM comprehension of Word, Excel, and PowerPoint using native file formats (.docx, .xlsx, .pptx) and variants.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How is OCB organized in terms of evaluation tracks?",{"text":68,"@type":64},"OCB has two tracks: File Fidelity Q&A for structural and visual perception, and Domain Q&A for expert-level reasoning across 12 professional domains.",{"name":70,"@type":61,"acceptedAnswer":71},"How are responses scored in OCB?",{"text":72,"@type":64},"Each reference answer is decomposed into atomic, binary-gradable claims, and an ensemble of LLM judges scores responses against each claim independently, using a majority-vote approach.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},327140,1790318594,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,127],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":140,"language":141,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":12,"update_tm":145,"read_time":146,"preview_page_count":4},8796095360427,"https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d","Office Comprehension Benchmark  \nFiroz Shaik, Mateus Picanço Lima Gomes†, Tanvir Aumi, Jingci Wang, Milos Milunovic  \nFilip Basara, Ivana Jovanovic, Vishwas Suryanarayanan, Neha Nandan Kenkare, Weiyao Xie Zhipeng Han, Zheng Zhang, Waleed Shahid, Jay Rathi, Russell Scherer Thong Q. Nguyen†, Michael Bentley, Tamara Stankovic, Rasika Chakravarthy, Vishal Chowdhary  \nMicrosoft  \n† Work done while at Microsoft.  \nCorrespondence: [firozshaik@microsoft.com](firozshaik@microsoft.com)  \narXiv :2607 .01245v1 [ cs .CL] 29 May 2026  \nAbstract  \nWe introduce Office Comprehension Bench (OCB), the first public benchmark to jointly evaluate LLM systems on Word, Excel, and PowerPoint comprehension over native file formats ( .docx, .xlsx, .pptx) and their variants. OCB consists of two tracks. File Fidelity Q&A tests structural and visual perception of office artifacts-tables, charts, embedded images, formulas, and app-specific elements such as headers, speaker notes, and named ranges. Domain Q&A tests expert-level reasoning grounded in real-world industry documents across 12 professional domains, with queries requiring multi-step analysis and synthesis across documents. Each reference answer is decomposed into atomic, binary-gradable claims, and an ensemble of LLM judges scores responses against each claim independently. Even the strongest frontier system in its default reasoning mode reaches only ∼59.3% on Domain Q&A; increasing thinking depth within a tier does not move performance materially, while moving to a higher product tier yields modest gains. We release the dataset, evaluation tooling, judge prompt, and a public leaderboard.  \nDate: May 2026  \nData: [huggingface.co/datasets/microsoft/](huggingface.co/datasets/microsoft/)[ ](huggingface.co/datasets/microsoft/)OfficeComprehensionBenchmark  \nCode: [github.com/microsoft/](github.com/microsoft/)[ ](github.com/microsoft/)OfficeComprehensionBench  \n1 Introduction  \nOffice documents are a primary medium for knowledge work, combining free-form text, structured tables, embedded images, charts, and applicationspecific constructs (e.g., slide layouts, document styles, and spreadsheets with formulas) . Despite rapid progress in large language models (LLMs), rigorous evaluation of office comprehension remains limited. Office tasks often require grounded reading over a file, multi-step reasoning over heterogeneous structure, and adherence to precise output formats. We introduce Office Comprehension Bench (OCB), a benchmark suite covering Word, Excel, and PowerPoint comprehension over native file formats ( .docx, .xlsx, .pptx) and their variants. To our knowledge, OCB is the first public benchmark to jointly evaluate comprehension overall three Office applications in their native file formats under a unified evaluation methodology. OCB consists of two complementary evaluation tracks:  \n• File Fidelity Q&A-240 files, 902 queries, and 1,305 atomic assertions evaluating whether a system can accurately perceive structural and visual content (tables, charts, images, slide layouts, formatting) .  \n• Domain Q&A - 64 files, 120 queries, and 5,414 atomic assertions evaluating expertlevel comprehension across 12 industries (finance, healthcare, manufacturing, accounting, energy, government, education, and others) . Domain queries require multi-step domain reasoning and synthesis across documents; a single response may produce dozens of independently verifiable claims.  \nOCB is comprehension-only by design and is complementary to agentic benchmarks that grade automation workflows or work-product creation (e.g., OfficeBench (Wang et al., 2024), Odyssey-  \nBench (Wang et al., 2025), GDPval (Patwardhan et al., 2025)), since reliable comprehension is a prerequisite for trustworthy automation and authoring.  \nWe release the dataset, evaluation tooling, an official LLM-as-a-judge accuracy prompt, and a public leaderboard reporting results for OpenAIGPT-5.5 Thinking, Anthropic Claude Opus 4.7, and Google Gemini 3.1 P","cbCaihnCDiq6leCf","https://ap.wps.com/l/cbCaihnCDiq6leCf","pdf",2115116,32,"English","# Introduction\n## OCB overview and evaluation tracks\n## Contributions and scope","[{\"question\":\"What does the Office Comprehension Bench (OCB) evaluate?\",\"answer\":\"OCB evaluates LLM comprehension of Word, Excel, and PowerPoint using native file formats (.docx, .xlsx, .pptx) and variants.\"},{\"question\":\"How is OCB organized in terms of evaluation tracks?\",\"answer\":\"OCB has two tracks: File Fidelity Q\\u0026A for structural and visual perception, and Domain Q\\u0026A for expert-level reasoning across 12 professional domains.\"},{\"question\":\"How are responses scored in OCB?\",\"answer\":\"Each reference answer is decomposed into atomic, binary-gradable claims, and an ensemble of LLM judges scores responses against each claim independently, using a majority-vote approach.\"}]","Office Comprehension Benchmark - May 2026 - Abstract | PDF",1789976521,81]