Integrating Artificial Intelligence and Science Education to Support Computational Thinking: A Multi-Model Benchmarking Study in Primary Numeracy
Downloads
Purpose of the study: This study investigates the multidisciplinary integration of artificial intelligence, learning analytics, cognitive psychology, and science education to evaluate three Large Language Model (LLM) configurations. It aims to optimize an adaptive digital scaffolding framework for primary computational thinking (CT) and scientific reasoning under tight latency constraints.
Methodology: Deployed via Python 3.11 within an automated benchmarking ecosystem, OpenAI gpt-5-mini, Google gemini-3.5-flash, and Meta llama-3.3-70b-versatile (Groq LPU) were evaluated across 15 Bebras tasks (135 structured API interactions). The multidisciplinary validation applied content and psycholinguistic triage to analyze the interface between technical inference latency and the continuity of students' scientific inquiry processes.
Main Findings: Meta Llama-3.3-70b achieved optimal performance with a 0.2687s latency, maximizing the Student Waiting Threshold (SWT) compliance margin to support uninterrupted scientific schema construction. OpenAI GPT-5 Mini exhibited superior Socratic instruction adherence (6.9% failure) but introduced a 2.3764s latency overhead. Gemini 3.5 Flash truncated crucial pedagogical contexts due to its constrained 3-token output distribution.
Novelty/Originality of this study: This work introduces a multidisciplinary engineering blueprint that bridges hardware-level computing optimization with technology-enhanced science education. By formalizing a latency-constrained routing protocol, it establishes a theoretical model demonstrating how infrastructure responsiveness directly safeguards the cognitive sustainability of scientific reasoning and problem-solving sequences in primary STEM learning contexts.
Downloads
S. K. Nordby, L. Mifsud, and A. H. Bjerke, “Computational thinking in primary mathematics classroom activities,” Front. Educ., vol. 9, 2024, doi: 10.3389/feduc.2024.1414081.
S. K. Nordby, A. H. Bjerke, and L. Mifsud, “Computational thinking in the primary mathematics classroom: A systematic review,” Digit. Exp. Math. Educ., vol. 8, no. 1, pp. 27–49, Apr. 2022, doi: 10.1007/s40751-022-00102-5.
V. Barr and C. Stephenson, “Bringing computational thinking to K–12: What is involved and what is the role of the computer science education community?,” ACM Trans. Comput. Educ., vol. 11, no. 1, pp. 1–11, Mar. 2011, doi: 10.1145/1929887.1929905.
K. Bati, “A systematic literature review regarding computational thinking and programming in early childhood education,” Educ. Inf. Technol., vol. 27, no. 2, pp. 2059–2082, Mar. 2022, doi: 10.1007/s10639-021-10700-2.
W. Welyta and M. G. Vega, “Discovery learning and scientific literacy: Integrating PISA indicators in high school science,” J. Acad. Biol. Biol. Educ., vol. 2, no. 1, pp. 79–87, Jun. 2025, doi: 10.37251/jouabe.v2i1.1941.
J. B. Khamali and H. O. Mondoh, “The effect of flash-based learning media on students’ achievement in learning atomic structure in Kenyan senior high schools,” J. Chem. Learn. Innov., vol. 2, no. 2, pp. 186–192, Dec. 2025, doi: 10.37251/jocli.v2i2.2584.
J. Su and W. Yang, “A systematic review of integrating computational thinking in early childhood education,” Comput. Educ. Open, vol. 4, p. 100122, Dec. 2023, doi: 10.1016/j.caeo.2023.100122.
H. Riah, “Augmented reality-based interactive learning media: Enhancing understanding of chemical bonding concepts,” J. Chem. Learn. Innov., vol. 2, no. 1, pp. 55–63, Jun. 2025, doi: 10.37251/jocli.v2i1.1919.
R. Rosana, A. Darda, and Z. Zaenudin, “The effect of using offline web-based interactive multimedia on students’ biology learning outcomes,” J. Acad. Biol. Biol. Educ., vol. 1, no. 2, pp. 177–185, Dec. 2024, doi: 10.37251/jouabe.v1i2.3178.
P. Chen, D. Yang, A. H. S. Metwally, J. Lavonen, and X. Wang, “Fostering computational thinking through unplugged activities: A systematic literature review and meta-analysis,” Int. J. STEM Educ., vol. 10, no. 1, 2023, doi: 10.1186/s40594-023-00434-7.
Y. H. Ching and Y. C. Hsu, “Educational robotics for developing computational thinking in young learners: A systematic review,” TechTrends, vol. 68, no. 3, pp. 423–434, May 2024, doi: 10.1007/s11528-023-00841-1.
S. Tao, “Aligning technology with cognitive development: A five-tiered framework for generative AI in K–12 education,” AI Brain Child, vol. 1, no. 1, 2025, doi: 10.1007/s44436-025-00024-0.
M. Vendrell and S. K. Johnston, “Scaffolding critical thinking with generative AI: Design principles for integrating large language models in higher education,” Comput. Educ.: Artif. Intell., vol. 10, p. 100572, Jun. 2026, doi: 10.1016/j.caeai.2026.100572.
T. K. F. Chiu, “Applying the self-determination theory (SDT) to explain student engagement in online learning during the COVID-19 pandemic,” J. Res. Technol. Educ., vol. 54, no. S1, pp. S14–S30, 2022, doi: 10.1080/15391523.2021.1891998.
L. El-Hamamsy, A. Kilic, M. Seiter, F. Heitzmann, U. Bergner, S. M. Volpe, and T. Reuter, “The competent computational thinking test (cCTt): A valid, reliable and gender-fair test for longitudinal CT studies in grades 3–6,” Technol. Knowl. Learn., vol. 30, no. 3, pp. 1607–1661, Sep. 2025, doi: 10.1007/s10758-024-09777-8.
H. S. Hsiao, Y. W. Lin, K. Y. Lin, C. Y. Lin, J. H. Chen, and J. C. Chen, “Using robot-based practices to develop an activity that incorporated the 6E model to improve elementary school students’ learning performances,” Interact. Learn. Environ., vol. 30, no. 1, pp. 85–99, 2022, doi: 10.1080/10494820.2019.1636090.
J. Fagerlund, P. Häkkinen, M. Vesisenaho, and J. Viiri, “Computational thinking in programming with Scratch in primary schools: A systematic review,” Comput. Appl. Eng. Educ., vol. 29, no. 1, pp. 12–28, Jan. 2021, doi: 10.1002/cae.22255.
R. Tariq, B. M. Aponte Babines, J. Ramirez, I. Alvarez-Icaza, and F. Naseer, “Computational thinking in STEM education: Current state-of-the-art and future research directions,” Front. Comput. Sci., vol. 6, 2024, doi: 10.3389/fcomp.2024.1480404.
E. A. Kyza, Y. Georgiou, A. Agesilaou, and M. Souropetsis, “A cross-sectional study investigating primary school children’s coding practices and computational thinking using ScratchJr,” J. Educ. Comput. Res., vol. 60, no. 1, pp. 220–257, Mar. 2022, doi: 10.1177/07356331211027387.
X. Liu, X. Wang, K. Xu, and X. Hu, “Effect of reverse engineering pedagogy on primary school students’ computational thinking skills in STEM learning activities,” J. Intell., vol. 11, no. 2, Art. no. 36, Feb. 2023, doi: 10.3390/jintelligence11020036.
U. H. Rusmin, A. Awaluddin, and M. T. Ajadi, “Development of Nusa Ra Island as a marine tourism object in increasing regional original income (PAD) in South Halmahera Regency,” Multidiscip. J. Tour. Hosp. Sport Phys. Educ., vol. 1, no. 2, pp. 50–59, 2024, doi: 10.37251/jthpe.v1i2.1188.
S. Zhang, C. D. Jaldi, N. L. Schroeder, A. A. López, J. R. Gladstone, and S. Heidig, “Pedagogical agent design for K–12 education: A systematic review,” Comput. Educ., vol. 223, Dec. 2024, Art. no. 105165, doi: 10.1016/j.compedu.2024.105165.
J. B. Bush, “Software-based intervention with digital manipulatives to support student conceptual understandings of fractions,” Br. J. Educ. Technol., vol. 52, no. 6, pp. 2299–2318, Nov. 2021, doi: 10.1111/bjet.13139.
S. Sharman, U. Axunov, and M. A. Balushi, “A study of reflective practice within a multidisciplinary team in an elite football academy,” Multidiscip. J. Tour. Hosp. Sport Phys. Educ., vol. 2, no. 1, pp. 41–49, 2025, doi: 10.37251/jthpe.v2i1.1856.
S. C. Shih, C. C. Chang, B. C. Kuo, and Y. H. Huang, “Mathematics intelligent tutoring system for learning multiplication and division of fractions based on diagnostic teaching,” Educ. Inf. Technol., vol. 28, no. 7, pp. 9189–9210, Jul. 2023, doi: 10.1007/s10639-022-11553-z.
R. H. Huang, D. J. Liu, A. Tlili, Y. Yang, and J. F. Wang, Handbook on Facilitating Flexible Learning During Educational Disruption: The Chinese Experience in Maintaining Undisrupted Learning in COVID-19 Outbreak. Beijing, China: Smart Learning Institute of Beijing Normal University, Mar. 2020. [Online]. Available: http://creativecommons.org/licenses/by-sa/3.0/igo/
D. Najmudin, L. Susanti, and I. Pebrian, “Digital transformation in education: Challenges and opportunities in the age of AI,” Pedagogia, vol. 23, no. 1, Jun. 2025, doi: 10.17509/pdgia.v23i1.78405.
Y. Copur-Gencturk, J. Li, and S. Atabas, “Improving teaching at scale: Can AI be incorporated into professional development to create interactive, personalized learning for teachers?,” Am. Educ. Res. J., vol. 61, no. 4, pp. 767–802, Aug. 2024, doi: 10.3102/00028312241248514.
T. Son, “Intelligent tutoring systems in mathematics education: A systematic literature review using the substitution, augmentation, modification, redefinition model,” Computers, vol. 13, no. 10, Oct. 2024, Art. no. 270, doi: 10.3390/computers13100270.
Y. F. Lee, G. J. Hwang, and P. Y. Chen, “Technology-based interactive guidance to promote learning performance and self-regulation: A chatbot-assisted self-regulated learning approach,” Educ. Technol. Res. Dev., vol. 73, no. 4, pp. 2279–2304, Aug. 2025, doi: 10.1007/s11423-025-10478-x.
T. K. F. Chiu, “A classification tool to foster self-regulated learning with generative artificial intelligence by applying self-determination theory: A case of ChatGPT,” Educ. Technol. Res. Dev., vol. 72, no. 4, pp. 2401–2416, Aug. 2024, doi: 10.1007/s11423-024-10366-w.
C. C. Chien, H. Y. Chan, and H. T. Hou, “Learning by playing with generative AI: Design and evaluation of a role-playing educational game with generative AI as scaffolding for instant feedback interaction,” J. Res. Technol. Educ., vol. 57, no. 4, pp. 894–913, 2025, doi: 10.1080/15391523.2024.2338085.
F. Wang, X. Zhou, K. Li, A. C. K. Cheung, and M. Tian, “The effects of artificial intelligence-based interactive scaffolding on secondary students’ speaking performance, goal setting, self-evaluation, and motivation in informal digital learning of English,” Interact. Learn. Environ., vol. 33, no. 7, pp. 4633–4652, 2025, doi: 10.1080/10494820.2025.2470319.
P. Smutny and P. Schreiberova, “From rules to language models: A comparative study of chatbot learning assistants,” Front. Educ., vol. 11, May 2026, doi: 10.3389/feduc.2026.1794807.
S. Wang, et al., “Large language models for education: A survey and outlook,” IEEE Signal Process. Mag., vol. 42, no. 6, pp. 51–63, 2025, doi: 10.1109/MSP.2025.3594309.
A. Mannekote, et al., “Large language models for whole-learner support: Opportunities and challenges,” Front. Artif. Intell., vol. 7, 2024, doi: 10.3389/frai.2024.1460364.
A. Létourneau, M. Deslandes Martineau, P. Charland, J. A. Karran, J. Boasen, and P. M. Léger, “A systematic review of AI-driven intelligent tutoring systems (ITS) in K–12 education,” NPJ Sci. Learn., vol. 10, no. 1, 2025, doi: 10.1038/s41539-025-00320-7.
S. Moon, et al., “A latency processing unit: A latency-optimized and highly scalable processor for large language model inference,” IEEE Micro, vol. 44, no. 6, pp. 17–33, 2024, doi: 10.1109/MM.2024.3420728.
S. Jiang and G. K. W. Wong, “Exploring age and gender differences of computational thinkers in primary school: A developmental perspective,” J. Comput. Assist. Learn., vol. 38, no. 1, pp. 60–75, Feb. 2022, doi: 10.1111/jcal.12591.
F. Fang, Y. Tan, M. A. Messerschmidt, W. Yin, O. Nov, and A. Messerschmidt, “The impact of response latency and task type on human–LLM interaction and perception,” in Proc. CHI Conf. Hum. Factors Comput. Syst. (CHI ’26), Barcelona, Spain, Apr. 2026, Art. no. 17, doi: 10.1145/3772318.
T. K. F. Chiu, “Student engagement in K–12 online learning amid COVID-19: A qualitative approach from a self-determination theory perspective,” Interact. Learn. Environ., vol. 31, no. 6, pp. 3326–3339, 2023, doi: 10.1080/10494820.2021.1926289.
E. H. S. Y. Elim, “Promoting cognitive skills in AI-supported learning environments: The integration of Bloom’s taxonomy,” Educ. 3–13, 2024, doi: 10.1080/03004279.2024.2332469.
J. Sweller, “Cognitive load during problem solving: Effects on learning,” Cogn. Sci., vol. 12, no. 2, pp. 257–285, Apr. 1988, doi: 10.1207/s15516709cog1202_4.
C. Romero and S. Ventura, “Educational data mining and learning analytics: An updated survey,” Wiley Interdiscip. Rev. Data Min. Knowl. Discov., vol. 10, no. 3, p. e1355, May 2020, doi: 10.1002/widm.1355.
L. Kohnke, D. Zou, and H. Xie, “Microlearning and generative AI for pre-service teacher education: A qualitative case study,” Educ. Inf. Technol., vol. 30, no. 15, pp. 21221–21248, 2025, doi: 10.1007/s10639-025-13606-5.
A. Kumar, “Design and performance optimization of server-side rendering systems in modern web applications,” J. Inf. Syst. Eng. Manag., vol. 9, no. 3, Sep. 2024, Art. no. 76, doi: 10.52783/jisem.v9i3.76.
D. Weintrop, et al., “Defining computational thinking for mathematics and science classrooms,” J. Sci. Educ. Technol., vol. 25, no. 1, pp. 127–147, Feb. 2016, doi: 10.1007/s10956-015-9581-5.
M. Zapata-Cáceres, P. Marcelino, L. El-Hamamsy, and E. Martín-Barroso, “A Bebras computational thinking (ABC-Thinking) program for primary school: Evaluation using the competent computational thinking test,” Educ. Inf. Technol., vol. 29, no. 12, pp. 14969–14998, Aug. 2024, doi: 10.1007/s10639-023-12441-w.
V. Dagienė and G. Futschek, “Bebras international contest on informatics and computer literacy: Criteria for good tasks,” in Informatics Education—Supporting Computational Thinking, R. T. Mittermeir and M. M. Sysło, Eds., Lecture Notes in Computer Science, vol. 5090. Berlin, Germany: Springer, 2008, pp. 19–30, doi: 10.1007/978-3-540-69924-8_2.
L. El-Hamamsy, M. Zapata-Cáceres, E. Martín-Barroso, F. Mondada, J. D. Zufferey, and B. Bruno, “The competent computational thinking test: Development and validation of an unplugged computational thinking test for upper primary school,” J. Educ. Comput. Res., vol. 60, no. 7, pp. 1818–1866, Dec. 2022, doi: 10.1177/07356331221081753.
F. Heintz, L. Mannila, and T. Färnqvist, “A review of models for introducing computational thinking, computer science and computing in K–12 education,” in Proc. IEEE Front. Educ. Conf. (FIE), 2016, pp. 1–9, doi: 10.1109/FIE.2016.7757410.
Y. M. Al-Yafaei, N. J. Jomaa, and R. A. Attamimi, Eds., Human-Centered Approaches to AI-Enhanced English Language Learning and Teaching. Hershey, PA, USA: IGI Global Scientific Publishing, 2026, doi: 10.4018/979-8-3373-3561-2..
M. Tran, C. Balasooriya, C. Semmler, and J. Rhee, “Generative artificial intelligence: The ‘more knowledgeable other’ in a social constructivist framework of medical education,” NPJ Digit. Med., vol. 8, no. 1, p. 430, 2025, doi: 10.1038/s41746-025-01823-8.
R. Moreno and B. Park, “Cognitive load theory: Historical development and relation to other theories,” in Cognitive Load Theory, J. L. Plass, R. Moreno, and R. Brünken, Eds. Cambridge, U.K.: Cambridge Univ. Press, 2010, pp. 9–28, doi: 10.1017/CBO9780511844744.003.
L. Cai, M. M. Msafiri, and D. Kangwa, “Exploring the impact of integrating AI tools in higher education using the zone of proximal development,” Educ. Inf. Technol., vol. 30, no. 6, pp. 7191–7264, 2025, doi: 10.1007/s10639-024-13112-0.
İ. Çetin, A. K. Erümit, V. Nabiyev, H. Karal, T. Kösa, and M. Kokoç, “The effect of gamified adaptive intelligent tutoring system Artibos on problem-solving skills,” Particip. Educ. Res., vol. 10, no. 1, pp. 344–374, 2023, doi: 10.17275/per.23.19.10.1.
H. Bai, W. C. Lui, and P. V. Khiatani, “Promoting student engagement with GPTutor: An intelligent tutoring system powered by generative AI,” Int. J. Educ. Technol. High. Educ., vol. 22, no. 1, 2025, doi: 10.1186/s41239-025-00571-9.
I. H. Y. Yim and J. Su, “Artificial intelligence (AI) learning tools in K–12 education: A scoping review,” J. Comput. Educ., vol. 12, no. 1, pp. 93–131, Mar. 2025, doi: 10.1007/s40692-023-00304-9.
Copyright (c) 2026 Suprih Widodo, Muhamad Akda Fathul Barri, Ayu Permata Sari, Hapizah Hapizah, Intan Sari Rufiana, Sumarni Sumarni, Zuriani Mustaffa
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and acknowledge that the Journal of Educational Technology and Learning Creativity is the first publisher licensed under a Creative Commons Attribution 4.0 International License.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges and earlier and greater citation of published work.
.png)
.png)
.png)
