A Comparison of DeepSeek and other LLMs.

Recently, DeepSeek has been the focus of attention in and beyond the AI community. An interesting problem is how DeepSeek compares to other large language models (LLMs). There are many tasks an LLM can do, and in this article, we use the task of predicting an outcome using a short text for compariso...

Descripción completa

Detalles Bibliográficos
Publicado en:American Statistician Vol. 80; no. 1; pp. 164 - 177
Autores principales: Gao, Tianchen, Jin, Jiashun, Ke, Zheng Tracy, Moryoussef, Gabriel
Formato: Artículo
Publicado: Taylor & Francis Ltd Feb2026
Materias:
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ssf&AN=191630194&site=ehost-live
header:
  @attributes:
    shortDbName: ssf
    uiTerm: 191630194
    longDbName: Social Sciences Full Text (H.W. Wilson)
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        00031305
        STT
      jtl: American Statistician
      issn: 00031305
      maglogo: Y
    pubinfo:
      dt: Feb2026
      vid: 80
      iid: 1
      pid: 377
      pub: Taylor & Francis Ltd
    artinfo:
      ui:
        191630194
        10.1080/00031305.2025.2611010
      ppf: 164
      ppct: 13
      formats:
      tig:
        atl: A Comparison of DeepSeek and other LLMs.
      aug:
        au:
          Gao, Tianchen
          Jin, Jiashun
          Ke, Zheng Tracy
          Moryoussef, Gabriel
        affil:
          Beijing International Center for Mathematical Research, Peking University, Beijing, China
          Department of Statistics & Data Science, Carnegie Mellon University, Pittsburgh, PA
          Department of Statistics, Harvard University, Cambridge, MA
      su:
        Electronic data processing
        Language models
        Classification
        Attribution of authorship
        Benchmark problems (Computer science)
      sug:
        subj:
          Electronic data processing
          Data Processing, Hosting, and Related Services
          Language models
          Classification
          Attribution of authorship
          Benchmark problems (Computer science)
      keyword:
        AI-generated text detection
        Citation classification
        MADStat
        Prompt
        Text analysis
        Textual content
        AI-generated text detection
        Citation classification
        MADStat
        Prompt
        Text analysis
        Textual content
      ab: Recently, DeepSeek has been the focus of attention in and beyond the AI community. An interesting problem is how DeepSeek compares to other large language models (LLMs). There are many tasks an LLM can do, and in this article, we use the task of predicting an outcome using a short text for comparison. We consider two settings, an authorship classification setting and a citation classification setting. In the first one, the goal is to determine whether a short text is written by human or AI. In the second one, the goal is to classify a citation into one of four types using the textual content. For each experiment, we compare DeepSeek with four popular LLMs: Claude, Gemini, GPT, and Llama. We find that, in terms of classification accuracy, DeepSeek outperforms Gemini, GPT, and Llama in most cases, but underperforms Claude. We also find that DeepSeek is comparably slower than others but with a low cost to use, while Claude is much more expensive than all the others. Finally, we find that in terms of similarity, the output of DeepSeek is most similar to those of Gemini and Claude (and among all five LLMs, Claude and Gemini have the most similar outputs). In this article, we also present a fully-labeled dataset collected by ourselves, and propose a recipe where we can use the LLMs and a recent dataset, MADStat, to generate new datasets. The datasets in our article can be used as benchmarks for future study on LLMs.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: N
    holdings:
      @attributes:
        islocal: N