Researchers have developed a new metric called the Pedagogical Suitability Index (PSI) to evaluate how well AI tutors align with a student's learning progress and curriculum. Existing evaluations primarily focus on the correctness of answers, neglecting the pedagogical appropriateness. The PSI metric, composed of six sub-scores, was used to assess four AI tutors: ChatGPT, Gemini, Gemma4, and Qwen3. While baseline differences between the models were modest, the PSI-guided feedback protocol significantly improved the performance of weak-performing cases, with 82.3% showing improvement. AI
IMPACT Highlights the need for more nuanced evaluation of AI tutors beyond simple correctness, suggesting a path to improve their educational effectiveness.
RANK_REASON Academic paper introducing a new metric and evaluation framework for AI tutors. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
