Bard achieves an integrated accuracy of 56% on dental licensing examinations¶

Claim · All claims
Evidence · 1 study · quant-synthesis r2 · 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? Bard achieved an integrated accuracy of 56% (95% CI: 52%-60%) on dental licensing examinations across 3 studies. → 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 · r2

Meta-analysis of 3 studies testing Bard on dental licensing examinations using a common effects model despite very high heterogeneity. The review reports "The integrated accuracy rate for Bard was 56% (95% CI: 52%-60%)".

"Because only three studies tested Bard, a common effects model was used, despite the I² being 91% (I² > 50%). The integrated accuracy rate for Bard was 56% (95% CI: 52%-60%)"

Discussion¶

Related Claims¶

• GPT-4 outperforms GPT-3.5 and Bard on dental licensing examinations, achieving an integrated accuracy of 72% — related
• GPT-4 achieves the highest pooled accuracy among LLMs (81%), significantly outperforming GPT-3.5 (60%) — reports the opposite
• Large language models achieve a pooled accuracy of 63.69% (95% CI 60.26%-67.06%) in answering dental examination questions — a broader claim this one bears on
• GPT-3.5 achieves an integrated accuracy of 54% on dental licensing examinations — related