[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-benchmark-finds-ai-models-struggle-to-read-chemical-patent-shorthand":10,"sections":34},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":24,"tags":25,"sources":29,"feedback":33,"feedback_at":22,"cost_usd":33,"total_tokens":33},9479,"benchmark-finds-ai-models-struggle-to-read-chemical-patent-shorthand","Benchmark Finds AI Models Struggle to Read Chemical Patent Shorthand","A new diagnostic test shows vision-language models ace easy chemistry questions but falter badly once patent shorthand gets genuinely hard to parse.","A new benchmark shows that AI models still can't reliably read the fill-in-the-blank chemistry notation patent lawyers use to describe entire families of drugs.\n\nResearchers built R-GroundBench, a diagnostic test drawn from real pharmaceutical patents, to probe how well AI models handle Markush structures - the placeholder notation (R1, R2, X, and so on) chemists use to describe whole families of related molecules in a single diagram. The benchmark includes multiple-choice questions at varying difficulty levels plus an open-ended generation task. Models did fine on easy questions, scoring over 90% accuracy. But accuracy dropped to 56-66% on harder questions designed to block shortcuts, and chemistry-specific models fared worse, managing only 25.7-46.2% despite being trained specifically on chemical data.\n\nMarkush structures are the backbone of how pharma companies protect intellectual property, covering thousands of possible compounds in a single patent claim. If AI tools are going to help with drug discovery or patent analysis, they need to parse this shorthand correctly, not just recognize familiar-looking diagrams. The open-ended generation task exposed an even bigger gap: exact-match accuracy fell below 20% for most models and below 8% when a model had to work from an image rather than text alone.\n\nSpecialized training didn't help much here - the chemistry-tuned models underperformed general ones on the hardest questions, a reminder that domain pretraining doesn't automatically buy domain reasoning.","[\"ai\",\"benchmarks\",\"chemistry\",\"drug-discovery\"]","2026-10-02T04:00:00.000Z","2026-10-02T21:19:01.626Z","2026-10-02T21:19:12.959Z","published",null,[],"ai",[24,26,27,28],"benchmarks","chemistry","drug-discovery",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.00700",0,{"sections":35},[36,39,43,48,53,58,62,67,72,77,82,87,92,97],{"name":37,"slug":24,"count":38,"latest_published_at":18},"AI",5817,{"name":40,"slug":41,"count":42,"latest_published_at":18},"Security","security",832,{"name":44,"slug":45,"count":46,"latest_published_at":47},"Policy","policy",437,"2026-10-01T18:10:00.000Z",{"name":49,"slug":50,"count":51,"latest_published_at":52},"Deals","deals",317,"2026-10-01T22:00:00.000Z",{"name":54,"slug":55,"count":56,"latest_published_at":57},"Hardware","hardware",198,"2026-10-01T17:38:48.000Z",{"name":59,"slug":60,"count":61,"latest_published_at":18},"Science","science",169,{"name":63,"slug":64,"count":65,"latest_published_at":66},"Consumer Tech","consumer-tech",155,"2026-10-01T19:54:10.000Z",{"name":68,"slug":69,"count":70,"latest_published_at":71},"Dev Tools","dev-tools",96,"2026-10-01T16:57:03.000Z",{"name":73,"slug":74,"count":75,"latest_published_at":76},"Software","software",93,"2026-09-30T21:41:11.000Z",{"name":78,"slug":79,"count":80,"latest_published_at":81},"Startups","startups",90,"2026-10-01T21:55:22.000Z",{"name":83,"slug":84,"count":85,"latest_published_at":86},"Gaming","gaming",53,"2026-10-02T02:50:39.000Z",{"name":88,"slug":89,"count":90,"latest_published_at":91},"General","general",50,"2026-09-30T21:37:54.000Z",{"name":93,"slug":94,"count":95,"latest_published_at":96},"Reviews","reviews",31,"2026-09-28T14:31:34.000Z",{"name":98,"slug":99,"count":100,"latest_published_at":101},"How-To","how-to",7,"2026-10-01T09:00:00.000Z"]