{"version":1,"type":"story","url":"https://digestai.news/story/cadworld-a-new-benchmark-for-long-horizon-computer-aided-design","json":"https://digestai.news/story/cadworld-a-new-benchmark-for-long-horizon-computer-aided-design.json","markdown":"https://digestai.news/story/cadworld-a-new-benchmark-for-long-horizon-computer-aided-design.md","slug":"cadworld-a-new-benchmark-for-long-horizon-computer-aided-design","headline":"CADWorld: A New Benchmark for Long-Horizon Computer-Aided Design","summary":"Computer-use agents are increasingly evaluated in realistic desktop environments, but benchmarks often lack coverage of professional engineering workflows. This article introduces CADWorld, a new benchmark specifically designed for long-horizon computer use in FreeCAD. It contains over 200 tasks across eleven mechanical-CAD workflow categories, including sketching, part modeling, assembly, CAM (Computer-Aided Manufacturing), FEM (Finite Element Method), measurement, mesh processing, and technical drawing. Agents operate through screenshots and GUI actions, with success determined by task-specific checks on saved FreeCAD artifacts and auxiliary outputs such as geometric properties, parametric structure, constraints, manufacturing state, and simulation results. The strongest agent achieves only 17.5% success rate compared to the 87.0% expert reference pass. This benchmark highlights a gap between general GUI competence and reliable execution of persistent engineering workflows.","keyPoints":["CADWorld introduces a new benchmark for long-horizon computer use in FreeCAD","Contains over 200 tasks across eleven mechanical-CAD workflow categories","Success determined by checks on saved FreeCAD artifacts and auxiliary outputs"],"whyItMatters":"This benchmark exposes a significant gap between general GUI competence and reliable execution of persistent engineering workflows, which is crucial for the development and evaluation of computer-aided design agents.","category":{"slug":"models","name":"Generative AI & Models","url":"https://digestai.news/category/models"},"entities":{"companies":[],"models":[],"people":[]},"firstPublishedAt":"2026-09-16T04:00:00Z","updatedAt":"2026-09-16T04:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"arXiv cs.AI","title":"CADWorld: Computer-Use Benchmark for Long-Horizon Computer-Aided Design","url":"https://arxiv.org/abs/2609.16251","publishedAt":"2026-09-16T04:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"CADWorld: A New Benchmark for Long-Horizon Computer-Aided Design\", 16 September 2026, https://digestai.news/story/cadworld-a-new-benchmark-for-long-horizon-computer-aided-design","publisher":"Digest AI","title":"CADWorld: A New Benchmark for Long-Horizon Computer-Aided Design","datePublished":"2026-09-16T04:00:00Z","url":"https://digestai.news/story/cadworld-a-new-benchmark-for-long-horizon-computer-aided-design"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}