Related Experiment Video
Updated: May 10, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
Can Generative AI and ChatGPT Break Human Supremacy in Mathematics and Reshape Competence in Cognitive-Demanding
1Department of Mathematics Education, Faculty of Education, Nevsehir Hacı Bektas Veli University, 50300 Nevsehir, Türkiye.
Generative AI tools like ChatGPT-4o and GPT-4 show strong performance on math assessments, often surpassing student scores. While they generally improve with cognitive demand, this effect was less pronounced at the 12th-grade level.
Area of Science:
- Artificial Intelligence
- Cognitive Science
- Educational Assessment
Background:
- Generative AI tools are increasingly explored for cognitive support.
- Understanding AI's impact on problem-solving and learning is crucial.
- The National Assessment of Educational Progress (NAEP) mathematics assessments provide a benchmark for student performance.
Purpose of the Study:
- To evaluate the performance of ChatGPT-4o and GPT-4 on NAEP mathematics assessments.
- To analyze AI performance in relation to cognitive complexity and demands.
- To compare AI capabilities with student performance across different grade levels.
Main Methods:
- Sixty NAEP mathematics assessment tasks were analyzed based on cognitive complexity.
- ChatGPT-4o and GPT-4 generated responses to these tasks.
- AI responses were scored using NAEP's established criteria.
- Performance was analyzed using average student scores and item-wise response percentages.
Main Results:
- ChatGPT-4o and GPT-4 outperformed most students on individual NAEP mathematics items.
- Higher cognitive demand correlated with a need for higher performance scores to answer correctly.
- This trend was consistent across 4th, 8th, and 12th grades.
Conclusions:
- Generative AI models demonstrate significant potential in mathematics problem-solving.
- AI performance shows sensitivity to cognitive demands, though with grade-level variations.
- Further research is needed to understand AI's nuanced interaction with complex cognitive tasks at higher education levels.
More Related Videos
10:26Problem-Solving Before Instruction PS-I: A Protocol for Assessment and Intervention in Students with Different Abilities
Published on: September 11, 2021
09:43Reversible Cooling-induced Deactivations to Study Cortical Contributions to Obstacle Memory in the Walking Cat
Published on: December 11, 2017
Related Concept Videos
Gauss's Law: Problem-Solving
Theorems of Pappus and Guldinus: Problem Solving
Introduction to Cognitive Psychology
This field emerged in the mid-20th century, following a period dominated by behaviorism, which...
Cognitivism
Previously dominated by behaviorism, which prioritized observable behaviors and largely ignored mental processes, psychology transformed in the 1950s. Cognitive psychologists argue that understanding how we think and process...
Non-equilibrium in the Cell
Cognitive Learning
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...