Meta-analysis including 27 articles (2022–2025): large language model accuracy on dentistry single-best-answer MCQs improved significantly over time, and OpenAI models outperformed others. Question type and source made no significant difference; heterogeneity was high.
Meta-analysisn = 27 studies
Doubleday et al. Temporal trends in large language model (LLM) accuracy: A meta-analysis of multiple-choice question performance in dentistry and dental education