{
  "abstract": "A rigorous statistical treatment of two-model comparisons on the same evals can be achieved by paired t-tests, analyzing their standard errors and a clustering correction for correlated questions. Nevertheless, leaderboards, ablations studies, and hyperparameter sweeps, usually compare $K>2$ models simultaneously. In this paper, we present a single random-effects model for scores on shared evals. We leverage models as a fixed effects and questions (or question cluster) as random effects. We show that fitting it a classical ANOVA or a linear mixed model we can recover Miller's paired and clustered estimators for K=2, but we extend the results to any K and to unbalanced, clustered designs. We validate the described model in a simulation study and using a real-data application. We take six openly available language models scored on 1,497 shared MMLU-Pro questions across 14 subject clusters, and we show that pairwise ranking claims survive depending on properly accounting for both question-level pairing and multiple comparisons. By the end of the manuscript, we provide concrete recommendations for reporting multi-model eval results.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2608.22659",
  "author_total": 1,
  "authors": [
    {
      "name": "Juan Francisco Mandujano Reyes"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/4md7a9evtwmy5.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2608.22659",
  "fulltext_url": null,
  "id": "4md7a9evtwmy5",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2608.22659",
  "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",
      "stat.AP"
    ],
    [
      "arxiv",
      "stat.ME"
    ],
    [
      "openalex",
      "2613|Statistical Methods and Applications"
    ]
  ],
  "openalex": "W7204187930",
  "pdf_url": "https://arxiv.org/pdf/2608.22659",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-18",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/4md7a9evtwmy5.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:33:54Z",
      "native_id": "2608.22659",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2608.22659"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.AP",
      "subfield": "statistics"
    }
  ],
  "title": "Statistical Methods for Multiple Language Model Comparison on a Shared Evaluation",
  "title_text": "Statistical Methods for Multiple Language Model Comparison on a Shared Evaluation",
  "type": "preprint",
  "updated_at": "2026-10-30T12:33:54Z",
  "url": "https://research.draconitic.com/paper/4md7a9evtwmy5",
  "venue": "arXiv",
  "versions": []
}