{"rewrite":{"id":"r_f5f6b5b5e84a392a93f28a4b","clusterId":"c_d668c411e654473cff117540","slug":"onestruction-releases-construction-ai-leaderboard-ranking-20-models","model":"deepseek-v4-1-flash","headline":"ONESTRUCTION Releases Construction AI Leaderboard Ranking 20 Models","summary":"ONESTRUCTION released the Construction AI Leaderboard on November 4, 2026, a site that ranks generative AI models on construction work. The Tottori City company evaluates 20 commercial and open models across five categories, from reading drawings and documents to editing BIM data and cost estimation. In results as of October 2026, Claude Opus 5.5 led the overall ranking at 73.7 points, with Gemini 4 Argon at 73.6. The top model differed in three of the five categories. All 20 models scored 85 points or higher on construction knowledge such as cost estimation, while drawing comprehension and BIM data understanding topped out in the 60 to 70 point range, with some small open models in single digits. A sixth category, BIM generation from drawings, is listed as coming soon. ONESTRUCTION is developing the Ishigaki construction-domain model through the third and fourth terms of GENIAC, a project run by METI and NEDO.","whyItMatters":"The leaderboard splits a single overall score into five task categories, and the split is the finding: cost-estimation ability is near-uniform across 20 models while drawing and BIM-data comprehension separates them, so procurement choices hinge on category rather than rank.","webCardHtml":"\u003cp\u003eThe IDS category uses Ishigaki-IDS-Bench, a benchmark proposed in an ONESTRUCTION paper accepted at CIKM 2026, and carries 166 questions. The other published categories are AEC-Bench for drawing and document understanding (196 tasks), IFC-Bench-V2 for BIM data understanding (514 questions), BIM-Edit for BIM data editing (324 tasks), and CEQuest for construction knowledge including cost estimation (134 questions). All models are run through the same procedure on a common platform built by ONESTRUCTION.\u003c/p\u003e\u003cp\u003eThe company says the rankings describe models at release under its own evaluation conditions and do not rate the technical capability of the organizations that develop them. ONESTRUCTION plans to add results as new models appear, and to post evaluations of its own Ishigaki series. The same day, ONESTRUCTION opened a waiting list for Ishigaki-BIM, a beta AI agent that generates BIM models from natural-language requirements and drawings, aimed at apartment and office buildings.\u003c/p\u003e\u003cul\u003e\u003cli\u003e\u003cstrong\u003eCreation of BIM information requirements (IDS)\u003c/strong\u003e: Ishigaki-IDS-Bench, 166 questions, benchmark from a paper accepted at CIKM 2026\u003c/li\u003e\u003cli\u003e\u003cstrong\u003eUnderstanding of drawings and documents\u003c/strong\u003e: AEC-Bench, 196 tasks\u003c/li\u003e\u003cli\u003e\u003cstrong\u003eUnderstanding of BIM data\u003c/strong\u003e: IFC-Bench-V2, 514 questions\u003c/li\u003e\u003cli\u003e\u003cstrong\u003eEditing of BIM data\u003c/strong\u003e: BIM-Edit, 324 tasks\u003c/li\u003e\u003cli\u003e\u003cstrong\u003eConstruction knowledge such as cost estimation\u003c/strong\u003e: CEQuest, 134 questions\u003c/li\u003e\u003cli\u003e\u003cstrong\u003eAbility to generate BIM from drawings\u003c/strong\u003e: BIMGenBench, listed as coming soon\u003c/li\u003e\u003c/ul\u003e","blueskyPost":"Claude Opus 5.5 leads ONESTRUCTION's Construction AI Leaderboard at 73.7 points as of October 2026, but the top model changed in three of five categories. On cost estimation, all 20 models cleared 85 points.","twitterPost":"The hardest construction task for general-purpose AI? Writing BIM information requirements. Best score there was 63.0 points, the lowest top score of the five ranked categories on ONESTRUCTION's new leaderboard.","threadsPost":null,"newsletterBlurb":"ONESTRUCTION published a leaderboard ranking 20 generative AI models on construction work, scored across five task categories. Overall leaders are close, but category winners differ, and drawing comprehension lags cost estimation badly. A sixth BIM generation category is promised later.","attributionJson":"[{\"source\":\"ASCII.jp\",\"url\":\"https://ascii.jp/elem/000/004/448/4448358/?rss\",\"title\":\"ONESTRUCTION Releases 'Construction AI Leaderboard' Comparing Generative AI Models' Ability to Handle Construction Work\"},{\"source\":\"ASCII.jp\",\"url\":\"https://ascii.jp/elem/000/004/448/4448357/?rss\",\"title\":\"ONESTRUCTION Begins Recruiting Test Participants for \\\"Ishigaki-BIM (β),\\\" an AI Agent That Generates BIM\"},{\"source\":\"ASCII.jp\",\"url\":\"https://ascii.jp/elem/000/004/448/4448356/?rss\",\"title\":\"ONESTRUCTION Begins API Provision of Construction Domain-Specific AI Model \\\"Ishigaki-AEC\\\" for GENIAC-PRIZE Applicant Companies\"}]","lintFlagsJson":null,"lintHits":0,"costUsd":0,"inputTokens":8541,"outputTokens":1238,"status":"published","repairAttempts":0,"nextRepairAt":null,"factsAttemptedAt":1793775912,"createdAt":"2026-11-04T07:01:54.000Z","publishedAt":"2026-11-04T07:03:51.000Z","updatedAt":"2026-11-04T07:03:51.000Z"},"cluster":{"id":"c_d668c411e654473cff117540","canonicalTitle":"ONESTRUCTION、生成AIモデルの建設業務への対応力を比較する「Construction AI Leaderboard」を公開","representativeArticleId":"a_ddc6856d12eade4257249324","sourceCount":1,"writtenSourceCount":1,"writeAttempts":0,"isSolo":false,"entitiesJson":"{\"anime_titles\":[],\"manga_titles\":[],\"work_titles\":[\"Ishigaki-AEC\",\"Ishigaki-BIM\",\"Construction AI Leaderboard\"],\"studios\":[\"ONESTRUCTION\"],\"people\":[],\"type\":\"news\",\"domain\":\"other\",\"is_roundup\":false}","contentType":"news","status":"published","firstSeenAt":"2026-11-04T03:52:56.000Z","lastSeenAt":"2026-11-04T03:55:56.000Z","updatedAt":"2026-11-04T07:03:52.000Z"},"attribution":[{"source":"ASCII.jp","url":"https://ascii.jp/elem/000/004/448/4448356/?rss","title":"ONESTRUCTION、建設ドメイン特化型AIモデル「Ishigaki-AEC」をGENIAC-PRIZE応募企業向けに API 提供開始"}],"entities":{"anime_titles":[],"manga_titles":[],"work_titles":["Ishigaki-AEC","Ishigaki-BIM","Construction AI Leaderboard"],"studios":["ONESTRUCTION"],"people":[],"type":"news","domain":"other","is_roundup":false},"keyFacts":["ONESTRUCTION released the Construction AI Leaderboard on November 4, 2026, evaluating 20 commercial and open generative AI models across five construction work categories.","Claude Opus 5.5 scored 73.7 points in the overall ranking as of October 2026, with Gemini 4 Argon at 73.6.","The top model differed in three of the five categories on the Construction AI Leaderboard.","The IDS category uses Ishigaki-IDS-Bench with 166 questions, drawn from an ONESTRUCTION paper accepted at CIKM 2026."],"pageLinks":{"healthSlugs":["ishigaki-aec","ishigaki-bim","construction-ai-leaderboard","onestruction"],"storySlugs":[],"entities":[{"slug":"ishigaki-aec","supported":0,"disputed":0,"contradicted":0,"unverified":1,"overall":"unverified","story_count":1,"has_dossier":false},{"slug":"ishigaki-bim","supported":0,"disputed":0,"contradicted":0,"unverified":0,"overall":"unverified","story_count":1,"has_dossier":false},{"slug":"construction-ai-leaderboard","supported":0,"disputed":0,"contradicted":0,"unverified":8,"overall":"unverified","story_count":1,"has_dossier":false},{"slug":"onestruction","supported":0,"disputed":0,"contradicted":0,"unverified":3,"overall":"unverified","story_count":1,"has_dossier":false}],"stories":[],"entitiesOk":true,"storiesOk":true}}