GPT-4 achieves the highest pooled accuracy among LLMs (81%), significantly outperforming GPT-3.5 (60%)¶

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? By model type, pooled accuracy was highest for GPT-4 (81%), followed by Bing (79%), Claude (74%), Gemini/Bard (70%), and GPT-3.5 (60%), with statistically significant differences among models (P=0.001). → Nouri Haniyeh 2025

Evidence¶

Nouri Haniyeh 2025¶

Nouri Haniyeh, Mahdavi Abdollah, Abedi Ali, Mohammadnia Alireza, Hamedan Mahnaz, Amanzadeh Masoud. (2025). Performance of large language models in medical licensing examinations: a systematic review and meta-analysis. Journal of Educational Evaluation for Health Professions. https://doi.org/10.3352/jeehp.2025.22.36

q3 · i? · quant-synthesis · r3

Subgroup analysis by LLM type across the 36 included studies (GPT-4 n=30, GPT-3.5 n=23, Bing n=4, Claude n=3, Gemini/Bard n=3). The review reports GPT-4 "pooled accuracy was highest" at 81% versus 60% for GPT-3.5, P=0.001.

"By model type, pooled accuracy was highest for GPT-4 (81%), followed by Bing (79%), Claude (74%), Gemini/Bard (70%), and GPT-3.5 (60%), with statistically significant differences among models (P=0.001)."

Discussion¶

Related Claims¶

• Newer Anthropic and DeepSeek models approach GPT‐4o–o1 accuracy on biomedical MCQs, while Google Gemini and Microsoft Copilot trail the leading companies — related
• GPT-4 achieves passing accuracy on USMLE Steps 1–3 (mean 86%), significantly exceeding GPT-3.5 (mean 56%) — related
• Large language models achieve a pooled accuracy of 72% on medical licensing examination questions across 36 studies — related
• Subgroup analyses show significant between-model differences, with Copilot (75.25%) and ChatGPT-4 (72.97%) achieving the highest pooled accuracies — related
• No significant difference in accuracy between ChatGPT 3.5 and Bard 1.0 generated MCQs — related
• ChatGPT-4.0 outperforms ChatGPT-3.5 in medical licensing exams, achieving a pooled accuracy of 81.8% versus 60.8% — possibly the same claim (merge candidate)
• Bard achieves an integrated accuracy of 56% on dental licensing examinations — reports the opposite
• GPT-4 outperforms GPT-3.5 and Bard on dental licensing examinations, achieving an integrated accuracy of 72% — related