View in EDS

Exploring the Performance of ChatGPT for Numerical Solution of Ordinary Differential Equations

Saved in:
Bibliographic Details
Title: Exploring the Performance of ChatGPT for Numerical Solution of Ordinary Differential Equations
Language: English
Authors: Saso Koceski (ORCID 0000-0002-5513-1898), Natasa Koceska (ORCID 0000-0002-3392-8871), Limonka Koceva Lazarova (ORCID 0000-0002-2759-0333), Marija Miteva (ORCID 0000-0001-5326-2301), Biljana Zlatanovska (ORCID 0000-0003-4300-2877)
Source: Journal of Technology and Science Education. 2025 15(1):18-34.
Availability: Journal of Technology and Science Education. ESEIAAT, Department of Projectes d'Enginyeria c/Colom 11, 08222 Terrassa, Spain. e-mail: info@jotse.org; e-mail: info@omniascience.com; Web site: http://www.jotse.org/index.php/jotse
Peer Reviewed: Y
Page Count: 17
Publication Date: 2025
Document Type: Journal Articles
Reports - Research
Descriptors: Artificial Intelligence, Technology Uses in Education, Number Concepts, Problem Solving, Equations (Mathematics), Mathematics Skills, Mathematical Applications, Programming, Coding, Accuracy, Difficulty Level, Input Output Analysis
ISSN: 2014-5349
2013-6374
Abstract: This study aims to evaluate ChatGPT's capabilities in certain numerical analysis problem: solving ordinary differential equations. The methodology which is developed in order to conduct this research takes into account the following mathematical abilities (defined according to National Centre for Education Statistics): Conceptual Understanding, Procedural Knowledge, Problem Solving, and Application in Real-world Contexts. The outcomes demonstrate that ChatGPT's performed very well for the set tasks, and it also gives promising results for programming code generation, with certain limitations. The effectiveness and accuracy of the answers and solutions obtained by ChatGPT are related to the type of equation, i.e., how complex it is, and also with the instructions we give to ChatGPT. It also requires further improvement of the machine learning model and the ability to provide an explanation of how the output was obtained.
Abstractor: As Provided
Entry Date: 2025
Accession Number: EJ1470563
Database: ERIC
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://eric.ed.gov/contentdelivery/servlet/ERICServlet?accno=EJ1470563
    Name: ERIC Full Text
    Category: fullText
    Text: Full Text from ERIC
Header DbId: eric
DbLabel: ERIC
An: EJ1470563
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Exploring the Performance of ChatGPT for Numerical Solution of Ordinary Differential Equations
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Saso+Koceski%22">Saso Koceski</searchLink> (ORCID <externalLink term="https://orcid.org/0000-0002-5513-1898">0000-0002-5513-1898</externalLink>)<br /><searchLink fieldCode="AR" term="%22Natasa+Koceska%22">Natasa Koceska</searchLink> (ORCID <externalLink term="https://orcid.org/0000-0002-3392-8871">0000-0002-3392-8871</externalLink>)<br /><searchLink fieldCode="AR" term="%22Limonka+Koceva+Lazarova%22">Limonka Koceva Lazarova</searchLink> (ORCID <externalLink term="https://orcid.org/0000-0002-2759-0333">0000-0002-2759-0333</externalLink>)<br /><searchLink fieldCode="AR" term="%22Marija+Miteva%22">Marija Miteva</searchLink> (ORCID <externalLink term="https://orcid.org/0000-0001-5326-2301">0000-0001-5326-2301</externalLink>)<br /><searchLink fieldCode="AR" term="%22Biljana+Zlatanovska%22">Biljana Zlatanovska</searchLink> (ORCID <externalLink term="https://orcid.org/0000-0003-4300-2877">0000-0003-4300-2877</externalLink>)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="SO" term="%22Journal+of+Technology+and+Science+Education%22"><i>Journal of Technology and Science Education</i></searchLink>. 2025 15(1):18-34.
– Name: Avail
  Label: Availability
  Group: Avail
  Data: Journal of Technology and Science Education. ESEIAAT, Department of Projectes d'Enginyeria c/Colom 11, 08222 Terrassa, Spain. e-mail: info@jotse.org; e-mail: info@omniascience.com; Web site: http://www.jotse.org/index.php/jotse
– Name: PeerReviewed
  Label: Peer Reviewed
  Group: SrcInfo
  Data: Y
– Name: Pages
  Label: Page Count
  Group: Src
  Data: 17
– Name: DatePubCY
  Label: Publication Date
  Group: Date
  Data: 2025
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: Journal Articles<br />Reports - Research
– Name: Subject
  Label: Descriptors
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Artificial+Intelligence%22">Artificial Intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Technology+Uses+in+Education%22">Technology Uses in Education</searchLink><br /><searchLink fieldCode="DE" term="%22Number+Concepts%22">Number Concepts</searchLink><br /><searchLink fieldCode="DE" term="%22Problem+Solving%22">Problem Solving</searchLink><br /><searchLink fieldCode="DE" term="%22Equations+%28Mathematics%29%22">Equations (Mathematics)</searchLink><br /><searchLink fieldCode="DE" term="%22Mathematics+Skills%22">Mathematics Skills</searchLink><br /><searchLink fieldCode="DE" term="%22Mathematical+Applications%22">Mathematical Applications</searchLink><br /><searchLink fieldCode="DE" term="%22Programming%22">Programming</searchLink><br /><searchLink fieldCode="DE" term="%22Coding%22">Coding</searchLink><br /><searchLink fieldCode="DE" term="%22Accuracy%22">Accuracy</searchLink><br /><searchLink fieldCode="DE" term="%22Difficulty+Level%22">Difficulty Level</searchLink><br /><searchLink fieldCode="DE" term="%22Input+Output+Analysis%22">Input Output Analysis</searchLink>
– Name: ISSN
  Label: ISSN
  Group: ISSN
  Data: 2014-5349<br />2013-6374
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: This study aims to evaluate ChatGPT's capabilities in certain numerical analysis problem: solving ordinary differential equations. The methodology which is developed in order to conduct this research takes into account the following mathematical abilities (defined according to National Centre for Education Statistics): Conceptual Understanding, Procedural Knowledge, Problem Solving, and Application in Real-world Contexts. The outcomes demonstrate that ChatGPT's performed very well for the set tasks, and it also gives promising results for programming code generation, with certain limitations. The effectiveness and accuracy of the answers and solutions obtained by ChatGPT are related to the type of equation, i.e., how complex it is, and also with the instructions we give to ChatGPT. It also requires further improvement of the machine learning model and the ability to provide an explanation of how the output was obtained.
– Name: AbstractInfo
  Label: Abstractor
  Group: Ab
  Data: As Provided
– Name: DateEntry
  Label: Entry Date
  Group: Date
  Data: 2025
– Name: AN
  Label: Accession Number
  Group: ID
  Data: EJ1470563
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=eric&AN=EJ1470563
RecordInfo BibRecord:
  BibEntity:
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 17
        StartPage: 18
    Subjects:
      – SubjectFull: Artificial Intelligence
        Type: general
      – SubjectFull: Technology Uses in Education
        Type: general
      – SubjectFull: Number Concepts
        Type: general
      – SubjectFull: Problem Solving
        Type: general
      – SubjectFull: Equations (Mathematics)
        Type: general
      – SubjectFull: Mathematics Skills
        Type: general
      – SubjectFull: Mathematical Applications
        Type: general
      – SubjectFull: Programming
        Type: general
      – SubjectFull: Coding
        Type: general
      – SubjectFull: Accuracy
        Type: general
      – SubjectFull: Difficulty Level
        Type: general
      – SubjectFull: Input Output Analysis
        Type: general
    Titles:
      – TitleFull: Exploring the Performance of ChatGPT for Numerical Solution of Ordinary Differential Equations
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Saso Koceski
      – PersonEntity:
          Name:
            NameFull: Natasa Koceska
      – PersonEntity:
          Name:
            NameFull: Limonka Koceva Lazarova
      – PersonEntity:
          Name:
            NameFull: Marija Miteva
      – PersonEntity:
          Name:
            NameFull: Biljana Zlatanovska
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 2014-5349
            – Type: issn-electronic
              Value: 2013-6374
          Numbering:
            – Type: volume
              Value: 15
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: Journal of Technology and Science Education
              Type: main
ResultId 1