الملخص
Chemical reaction-condition optimization -- choosing the catalyst, ligand, solvent, reagent, temperature, time, and atmosphere that jointly maximize yield and stereoselectivity -- is a central, judgement-laden subtask of organic methodology research that large language models are increasingly expected to support. Yet existing chemistry benchmarks evaluate reaction-class labelling, retrosynthesis, or SMILES manipulation, and do not ask models to read a real condition-screening table and pick the best set. We introduce RxnOptBench, a benchmark whose every option and precedent is a real wet-lab entry mined from the optimization tables of organic-methodology papers published in 2025, graded by a continuous relative score derived from a declared headline utility that combines reported yield with enantiomeric excess (ee), diastereomeric ratio (dr), and regioisomeric ratio (rr), and equipped with a paired precedents-vs-no-precedents design that isolates in-context use of literature evidence from parametric memorization. Across nine frontier LLMs and three Chemistry LLMs, even the best models leave substantial headroom: chemistry-specialized models fall to the random-baseline floor on multi-axis selection, while open-weight models have closed most of the gap to proprietary frontier models. We release the final human-reviewed benchmark test set and evaluation code.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Ge, L., Wang, Y., Gao, J., Song, J., Sun, J., Zhu, B., Yang, H., Wang, J., Ma, L., Wu, J., Li, Y., & He, C. (2026). RxnOptBench: Benchmarking LLMs for Reaction-Condition Optimization in Organic Methodology. https://omanscience.com/ar/articles/rxnoptbench-benchmarking-llms-for-reaction-condition-optimization-in-organic-methodology
MLA 9
Ge, Lingli, et al. "RxnOptBench: Benchmarking LLMs for Reaction-Condition Optimization in Organic Methodology." https://omanscience.com/ar/articles/rxnoptbench-benchmarking-llms-for-reaction-condition-optimization-in-organic-methodology.
شيكاغو (المؤلف–التاريخ)
Ge, Lingli, Yubin Wang, Junyuan Gao, Jiahe Song, Jiaxing Sun, Boyu Zhu, Haote Yang, Jingchao Wang, Lixin Ma, Jiang Wu, Yuqiang Li, and Conghui He. 2026. "RxnOptBench: Benchmarking LLMs for Reaction-Condition Optimization in Organic Methodology." https://omanscience.com/ar/articles/rxnoptbench-benchmarking-llms-for-reaction-condition-optimization-in-organic-methodology.
هارفارد
Ge, L., Wang, Y., Gao, J., Song, J., Sun, J., Zhu, B., Yang, H., Wang, J., Ma, L., Wu, J., Li, Y. and He, C. (2026) 'RxnOptBench: Benchmarking LLMs for Reaction-Condition Optimization in Organic Methodology', Available at: https://omanscience.com/ar/articles/rxnoptbench-benchmarking-llms-for-reaction-condition-optimization-in-organic-methodology.
فانكوفر
Ge L, Wang Y, Gao J, Song J, Sun J, Zhu B, et al. RxnOptBench: Benchmarking LLMs for Reaction-Condition Optimization in Organic Methodology. https://omanscience.com/ar/articles/rxnoptbench-benchmarking-llms-for-reaction-condition-optimization-in-organic-methodology
IEEE
L. Ge, Y. Wang, J. Gao, J. Song, J. Sun, B. Zhu, H. Yang, J. Wang, L. Ma, J. Wu, Y. Li, and C. He, "RxnOptBench: Benchmarking LLMs for Reaction-Condition Optimization in Organic Methodology," https://omanscience.com/ar/articles/rxnoptbench-benchmarking-llms-for-reaction-condition-optimization-in-organic-methodology.