{"schemaVersion":"nuwa-current-record-1","version":"2026-10-29.1","publication":"published","work":{"id":"rand-biological-benchmarking","title":"Toward Comprehensive Benchmarking of the Biological Knowledge of Frontier Large Language Models","aliases":[],"authors":["Sunishchal Dev","Charles Teague","Grant Ellison","Kyle Brady","Jeffrey Lee","Sarah L. Gebauer","Henry Alexander Bradley","Dawid Maciorowski","Bria Persaud","Jordan Despanie","Barbara Del Castello","Alyssa Worland","Michael Miller","Adrian Salas","Dave Nguyen","James Liu","Jason Johnson","Andrew Sloan","Will Stonehouse","Travis Merrill","Thomas Goode","McKelvey, Greg, Jr.","Ella Guest"],"primaryFunction":"evaluation","secondaryFunctions":[],"kind":"technical-report","sourceId":"rand-biological-benchmarking-publication","attributionSourceId":"rand-biological-benchmarking-publication","originalUrl":"https://www.rand.org/pubs/research_reports/RRA3797-1.html","publicationDate":"2025-11-25","updatedOn":"2026-10-25","areas":["cbrn"],"scopeNote":{"en":"Relevance is assigned to the research question and stated conditions of the work. A topic tag is not a risk rating.","zh":"风险关联依据研究问题及明确条件建立，主题标签不代表风险评级。"},"protocolIds":[],"contributions":[{"organizationId":"rand","role":"publisher","sourceId":"rand-biological-benchmarking-publication","locator":"Official publication masthead and article byline"}],"summary":{"en":"Compares biological-knowledge benchmarks and examines their suitability for assessing frontier-model misuse risks.","zh":"比较生物知识基准，并考察其评估前沿模型滥用风险的适用性。"},"note":{"question":null,"method":null,"finding":null,"supports":null,"limits":null,"connections":null},"resources":[],"noteStatus":{"question":"limited","method":"limited","finding":"limited","supports":"limited","limits":"limited","connections":"limited"},"noteAvailability":{"en":"A substantive NUWA research note is not yet available. The repeated draft sections were removed pending review of the original methods, findings and limitations; use the original publication for the research account.","zh":"实质性的 NUWA 研究笔记尚未完成。重复草稿章节已移除，待核查原始方法、发现与限制；研究内容请以原始出版物为准。"},"noteSourceLocator":"No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence.","tags":[]},"reading":{"id":"rand-biological-benchmarking","title":"Toward Comprehensive Benchmarking of the Biological Knowledge of Frontier Large Language Models","en":{"question":"What can existing biological/chemical knowledge and refusal benchmarks establish about frontier models?","design":"The official report summary compares models available by May 2025 on eight knowledge/refusal benchmarks and discusses human-baseline design.","findings":["The authors identify widespread benchmark saturation and frontier reasoning-model performance above several expert-question baselines.","Reducing refusals through the studied tuning also reduced some knowledge performance; risk effects remained unclear."],"interpretation":"NUWA interpretation: knowledge scores, refusal robustness and real-world uplift require separate evidence.","limits":"This reading covers the official overview, key takeaways and recommendations, not a complete report-methods audit.","decisionRelevance":"Model recommendation: prioritize qualified domain-matched human baselines, harder held-out items and implementation disclosure.","takeaway":"NUWA interpretation: knowledge scores, refusal robustness and real-world uplift require separate evidence.","connections":[],"scoring":null,"conditions":null,"statistics":null,"usage":"Model recommendation: prioritize qualified domain-matched human baselines, harder held-out items and implementation disclosure."},"zh":{"question":"既有生物化学知识与拒绝基准能说明前沿模型什么？","design":"官网报告概述比较截至2025年5月的模型，覆盖八项知识或拒绝基准，并讨论人类基线。","findings":["作者指出多个基准趋于饱和，前沿推理模型超部分专家题基线。","所测降低拒绝训练也降低部分知识表现，风险影响仍不明确。"],"interpretation":"NUWA 解读：知识得分、拒绝稳健性与现实增益需要不同证据。","limits":"此次阅读为官网概述、要点及建议，未完整审查报告方法。","decisionRelevance":"模型建议：重视匹配专长的人类基线、更难保留题及实现披露。","takeaway":"NUWA 解读：知识得分、拒绝稳健性与现实增益需要不同证据。","connections":[],"scoring":null,"conditions":null,"statistics":null,"usage":"模型建议：重视匹配专长的人类基线、更难保留题及实现披露。"},"assertionPolicy":{"question":"source-research-question","design":"source-finding","findings":"source-finding","interpretation":"nuwa-interpretation","limits":"source-limit-or-explicit-editorial-scope-limit","connections":"source-supported-relationship-only","decisionRelevance":"model-recommendation-not-source-conclusion"},"sourceRefs":[{"sourceId":"rand-biological-benchmarking-publication","url":"https://www.rand.org/pubs/research_reports/RRA3797-1.html","locator":"Report overview","version":"Selected original resource https://www.rand.org/pubs/research_reports/RRA3797-1.html; sha256:3a110b6e4b9c0f8c321b3c01015fa4ddc3052614e0585722c3c73cbc964f459b; archived source capture; exact capture time not independently established","artifactSha256":"3a110b6e4b9c0f8c321b3c01015fa4ddc3052614e0585722c3c73cbc964f459b"},{"sourceId":"rand-biological-benchmarking-publication","url":"https://www.rand.org/pubs/research_reports/RRA3797-1.html","locator":"Key Takeaways","version":"Selected original resource https://www.rand.org/pubs/research_reports/RRA3797-1.html; sha256:3a110b6e4b9c0f8c321b3c01015fa4ddc3052614e0585722c3c73cbc964f459b; archived source capture; exact capture time not independently established","artifactSha256":"3a110b6e4b9c0f8c321b3c01015fa4ddc3052614e0585722c3c73cbc964f459b"},{"sourceId":"rand-biological-benchmarking-publication","url":"https://www.rand.org/pubs/research_reports/RRA3797-1.html","locator":"Recommendations","version":"Selected original resource https://www.rand.org/pubs/research_reports/RRA3797-1.html; sha256:3a110b6e4b9c0f8c321b3c01015fa4ddc3052614e0585722c3c73cbc964f459b; archived source capture; exact capture time not independently established","artifactSha256":"3a110b6e4b9c0f8c321b3c01015fa4ddc3052614e0585722c3c73cbc964f459b"}],"publication":{"state":"published","publishedOn":"2026-10-29","authorizationReference":"user-authorized-global-index-publication-2026-10-29","reviewedCandidateId":"local-6efe31bc4a0c0f37"},"review":{"state":"published-note","sourceScope":"full-text","availableScope":null,"readingCoverage":"selected-source-sections; not a complete section-by-section paper audit","completePaperAudit":false,"independentEvidenceReview":"pending-human-review","bilingualEditorialReview":"pending-human-review","authorship":"model-assisted-research-note","preparedFingerprint":"19d26e2f3c0d35250f3d7cbeef2d700ede3a8887acdd989c9bcdab16bb69c266"}},"sources":[{"id":"rand-biological-benchmarking-publication","title":"Toward Comprehensive Benchmarking of the Biological Knowledge of Frontier Large Language Models","url":"https://www.rand.org/pubs/research_reports/RRA3797-1.html","version":"Source capture 2026-10-25","publicationDate":"2025-11-25","datePrecision":"day","type":"research-publication","verifiedOn":"2026-10-25","documentId":"https://www.rand.org/pubs/research_reports/RRA3797-1.html","authors":["Dev, Sunishchal","Teague, Charles","Ellison, Grant","Brady, Kyle","Lee, Jeffrey","Gebauer, Sarah L.","Bradley, Henry Alexander","Maciorowski, Dawid","Persaud, Bria","Despanie, Jordan","Del Castello, Barbara","Worland, Alyssa","Miller, Michael","Salas, Adrian","Nguyen, Dave","Liu, James","Johnson, Jason","Sloan, Andrew","Stonehouse, Will","Merrill, Travis","Goode, Thomas","McKelvey, Greg, Jr.","Guest, Ella"]}]}