{
  "abstract": "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.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.02242",
  "author_total": 12,
  "authors": [
    {
      "name": "Lingli Ge"
    },
    {
      "name": "Yubin Wang"
    },
    {
      "name": "Junyuan Gao"
    },
    {
      "name": "Jiahe Song"
    },
    {
      "name": "Jiaxing Sun"
    },
    {
      "name": "Boyu Zhu"
    },
    {
      "name": "Haote Yang"
    },
    {
      "name": "Jingchao Wang"
    },
    {
      "name": "Lixin Ma"
    },
    {
      "name": "Jiang Wu"
    },
    {
      "name": "Yuqiang Li"
    },
    {
      "name": "Conghui He"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/265gycsxjpyzg.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.02242",
  "fulltext_url": null,
  "id": "265gycsxjpyzg",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.02242",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "physics.chem-ph"
    ],
    [
      "openalex",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7220444821",
  "pdf_url": "https://arxiv.org/pdf/2610.02242",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/265gycsxjpyzg.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:26:45Z",
      "native_id": "2610.02242",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.02242"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "arxiv:physics.chem-ph",
      "subfield": "physical"
    }
  ],
  "title": "RxnOptBench: Benchmarking LLMs for Reaction-Condition Optimization in Organic Methodology",
  "title_text": "RxnOptBench: Benchmarking LLMs for Reaction-Condition Optimization in Organic Methodology",
  "type": "preprint",
  "updated_at": "2026-10-30T12:26:45Z",
  "url": "https://research.draconitic.com/paper/265gycsxjpyzg",
  "venue": "arXiv",
  "versions": []
}