Evaluating chatGPT-4 and chatGPT-4o: performance insights from NAEP mathematics problem solving

Artigo2024

Xin Wei

0 visualizações desta ficha 0 acessos ao texto completo Contagem real do Portal desde 25/09/2026; tráfego comum, sem testes; quem desativa o rastreamento no navegador não é contado.

Resumo

This study assesses the capabilities of OpenAI’s ChatGPT-4 and ChatGPT-4o in solving mathematics problems from the National Assessment of Educational Progress (NAEP) across grades 4, 8, and 12. Results indicate that ChatGPT-4o slightly outperform ChatGPT-4 and both models generally surpass U.S. students’ performance across all grades, content areas, item type, and difficulty level. However, both models perform worse on geometry and measurement than on algebra and face more difficulties with high-difficulty mathematics items. This investigation highlights the strengths and limitations of AI as a supplementary educational tool, pinpointing areas for improvement in spatial intelligence and complex mathematical problem-solving. These findings suggest that while AI has the potential to support instruction in specific mathematical areas like algebra, there remains a need for careful integration and teacher-mediated strategies in areas where AI is less effective.

Dados da obra

Tipo
Artigo
Periódico
Frontiers in Education, v. 9
Editora
Frontiers Media S.A.
Ano
2024 (2024-09)
Idioma
en
Palavras-chave
artificial intelligence; ChatGPT-4; ChatGPT-4o; NAEP; mathematics education
Temas
Álgebra, Avaliação, Geometria, Resolução de Problemas
DOI
10.3389/feduc.2024.1452570
ISSN
2504-284X
Acesso
Acesso aberto
Fontes
DOAJ — Directory of Open Access Journals
Na Biblioteca desde
01/10/2026 · verificada em 03/10/2026

Como citar

ABNT
WEI, Xin. Evaluating chatGPT-4 and chatGPT-4o: performance insights from NAEP mathematics problem solving. Frontiers in Education, v. 9, 2024. DOI: https://doi.org/10.3389/feduc.2024.1452570.

APA

Wei, X. (2024). Evaluating chatGPT-4 and chatGPT-4o: performance insights from NAEP mathematics problem solving. Frontiers in Education, 9. https://doi.org/10.3389/feduc.2024.1452570

BibTeX
@article{wei2024,
  author = {Wei, Xin},
  title = {Evaluating chatGPT-4 and chatGPT-4o: performance insights from NAEP mathematics problem solving},
  year = {2024},
  journal = {Frontiers in Education},
  volume = {9},
  publisher = {Frontiers Media S.A.},
  doi = {10.3389/feduc.2024.1452570},
  language = {en}
}
RIS
TY  - JOUR
AU  - Wei, Xin
TI  - Evaluating chatGPT-4 and chatGPT-4o: performance insights from NAEP mathematics problem solving
PY  - 2024
JO  - Frontiers in Education
VL  - 9
DO  - 10.3389/feduc.2024.1452570
LA  - en
ER  - 

Referência gerada automaticamente a partir dos metadados das fontes; confira com o documento original. Baixar BibTeX · Baixar RIS

Obras relacionadas

Obras do acervo corrente com mais temas em comum.

Acessibilidade

As escolhas valem em todas as páginas internas e ficam só neste navegador. Atalho: tecla de acesso 5.

Perfis rápidos

Ajustes

Sobre a acessibilidade do Portal