Can AI be a Teaching Partner? Evaluating ChatGPT, Gemini, and DeepSeek across Three Teaching Strategies

TL;DR

This study compares ChatGPT, Gemini, and DeepSeek as teaching agents across three pedagogical strategies, providing empirical evidence on their effectiveness in teaching programming to beginners.

Contribution

It introduces an evaluation protocol for assessing LLMs as pedagogical tools and compares their performance across different teaching strategies.

Findings

ChatGPT and Gemini scored higher than DeepSeek in pedagogical effectiveness.

Models showed similar patterns in Examples, Explanations, and Analogies strategies.

Performance varied with the Socratic Method, influenced by initial prompts.

Abstract

There are growing promises that Large Language Models (LLMs) can support students' learning by providing explanations, feedback, and guidance. However, despite their rapid adoption and widespread attention, there is still limited empirical evidence regarding the pedagogical skills of LLMs. This article presents a comparative study of popular LLMs, namely, ChatGPT, DeepSeek, and Gemini, acting as teaching agents. An evaluation protocol was developed, focusing on three pedagogical strategies: Examples, Explanations and Analogies, and the Socratic Method. Six human judges conducted the evaluations in the context of teaching the C programming language to beginners. The results indicate that LLM models exhibited similar interaction patterns in the pedagogical strategies of Examples and Explanations and Analogies. In contrast, for the Socratic Method, the models showed greater sensitivity to the pedagogical strategy and the initial prompt. Overall, ChatGPT and Gemini received higher scores, whereas DeepSeek obtained lower scores across the criteria, indicating differences in pedagogical performance across models.