{
  "abstract": "AimTo evaluate the accuracy, run-to-run consistency, and agreement of large language models on the Ukrainian Integrated Licensing Examination Krok 2 for the Specialty of Physical Therapy.\n\nMaterials and MethodsFive cloud-based LLMs (ChatGPT-5.5, Claude 5 Sonnet, Gemini 3.5 Flash, Grok 4, DeepSeek-V3) were evaluated using 150 Ukrainian-language multiple-choice questions from the official Krok 2 database. Each model completed two independent runs with identical inputs. Accuracy (with 95% confidence intervals, Wilson method), run-to-run consistency, and agreement were assessed. Statistical analysis included Cohens {kappa}, Cochrans Q and pairwise McNemar tests with Holm-Bonferroni correction.\n\nResultsAll models achieved >80% accuracy in both runs, exceeding the passing threshold of [≥]64%. In the first run, accuracy ranged from 80.00% (DeepSeek-V3) to 93.33% (Gemini 3.5 Flash); in the second run, from 82.67% (Claude 5 Sonnet) to 88.67% (Gemini 3.5 Flash). In the first run significant differences were observed between Gemini 3.5 Flash and Grok 4 (93.33% vs 84.00%; p=0.0022) and DeepSeek-V3 (93.33% vs 80.00%; p=0.0001). There were no statistically significant differences between models in the second run. R2R consistency exceeded 90% for all models with the highest in ChatGPT-5.5 (98.67%) and lowest in DeepSeek-V3 (90.00%). Cohens {kappa} ranged from 0.64 to 0.94, indicating substantial to almost perfect agreement. The stability of LLMs response correctness across two runs ranged from 77.33% (DeepSeek-V3) to 88.00% (Gemini 3.5 Flash).\n\nConclusionsAll LLMs demonstrated high performance on Ukrainian-language Krok 2 examination tasks. Gemini 3.5 Flash showed the highest accuracy in both runs and response correctness stability while ChatGPT-5.5 exhibited the greatest response consistency and agreement. Although the accuracy and stability of LLM responses may be interrelated, they represent distinct aspects of model performance. This highlights the need for a comprehensive approach to evaluating LLMs. The findings indicate the potential of LLMs as an auxiliary tool in the professional practice of physical therapy specialists.",
  "abstract_shown": true,
  "affiliations": [
    "Uzhhorod National University"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "name": "Y. F. Filak"
    },
    {
      "affs": [
        0
      ],
      "name": "Y. O. Mykhalko"
    },
    {
      "name": "M. V. Sabadosh"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9f653g3vk0rdd.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.21.26363368",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.09.21.26363368v1.full",
  "id": "9f653g3vk0rdd",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.09.21.26363368v1",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "medrxiv",
      "rehabilitation medicine and physical therapy"
    ],
    [
      "openalex",
      "2718|Artificial Intelligence in Healthcare and Education"
    ]
  ],
  "openalex": "W7214558572",
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.09.21.26363368v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-21",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/9f653g3vk0rdd.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:30Z",
      "native_id": "10.64898/2026.09.21.26363368",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.09.21.26363368v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2718|Artificial Intelligence in Healthcare and Education",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "Benchmarking large language models on the Ukrainian Krok 2 licensing examination in physical therapy: accuracy, consistency, and agreement",
  "title_text": "Benchmarking large language models on the Ukrainian Krok 2 licensing examination in physical therapy: accuracy, consistency, and agreement",
  "type": "preprint",
  "updated_at": "2026-10-30T12:19:30Z",
  "url": "https://research.draconitic.com/paper/9f653g3vk0rdd",
  "venue": "medRxiv",
  "versions": []
}