GPT-4 outperforms GPT-3.5 and Bard on dental licensing examinations, achieving an integrated accuracy of 72%¶

Claim · All claims
Evidence · 1 study · quant-synthesis r3 · q3
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person · recheck by 2028: tool and model accuracy changes quickly

Subclaims¶

q3 i? GPT-4 achieved an integrated accuracy of 72% (95% CI: 70%-74%) on dental licensing examinations, outperforming GPT-3.5 (54%) and Bard (56%). → Liu Mingxin 2025

Evidence¶

Liu Mingxin 2025¶

Liu Mingxin, Okuhara Tsuyoshi, Huang Wenbo, Ogihara Atsushi, Nagao Hikari Sophia, Okada Hiroko, Kiuchi Takahiro. (2025). Large Language Models in Dental Licensing Examinations: Systematic Review and Meta-Analysis. International Dental Journal. https://doi.org/10.1016/j.identj.2024.10.014

q3 · i? · quant-synthesis · r3

Meta-analysis of 7 studies testing GPT-4 on dental licensing examinations using a common effects model. The review reports "The integrate accuracy rate for GPT-4 was 72% (95% CI: 70%-74%)".

"In the results of GPT-4, since the I² was 24% (I² < 50%), a common effects model was used. The integrate accuracy rate for GPT-4 was 72% (95% CI: 70%-74%)"

Discussion¶

Related Claims¶

• Bard achieves an integrated accuracy of 56% on dental licensing examinations — related
• GPT-3.5 achieves an integrated accuracy of 54% on dental licensing examinations — related
• GPT-3.5 performs significantly better on dental licensing examinations from English-speaking countries than non-English-speaking countries — related
• GPT-4 achieves the highest pooled accuracy among LLMs (81%), significantly outperforming GPT-3.5 (60%) — related
• Subgroup analyses show significant between-model differences, with Copilot (75.25%) and ChatGPT-4 (72.97%) achieving the highest pooled accuracies — related
• Large language models achieve a pooled accuracy of 72% on medical licensing examination questions across 36 studies — a broader claim this one bears on
• Newer LLM versions generally outperformed older versions on dental examination questions — a broader claim this one bears on
• GPT-4's performance on dental licensing examinations does not differ significantly between English-speaking and non-English-speaking countries — related
• LLMs perform worse on dental licensing examinations than on medical licensing examinations — related