Comparison of ChatGPT-5.2 and DeepSeek-V3.2 responses to frequently asked patient questions about hallux valgus surgery

Aims: To compare ChatGPT-5.2 and DeepSeek-V3.2 responses to frequently asked patient questions about hallux valgus surgery in terms of accuracy, informativeness, comprehensibility, and currency. Methods: A Google search performed with a newly created account without previous search activity was used to identify patient-oriented questions about hallux valgus surgery. Two researchers reviewed 100 questions and consolidated overlapping items into 10 representative questions. On February 1, 2026, the same questions were submitted in English to ChatGPT-5.2 and DeepSeek-V3.2. The first response from each model was recorded without editing. Ten orthopedic specialists with at least five years of professional experience independently and blindly rated each response on a 5-point Likert scale for accuracy, informativeness, comprehensibility, and currency. Paired model scores were compared using the Wilcoxon signed-rank test. Results: Both models answered all 10 questions. ChatGPT-5.2 had numerically higher mean scores for accuracy (4.7±0.3 vs 4.6±0.4; p=0.214), informativeness (4.6±0.4 vs 4.4±0.5; p=0.081), comprehensibility (4.6±0.4 vs 4.5±0.4; p=0.197), and currency (4.5±0.4 vs 4.3±0.5; p=0.064). None of the between-model differences reached statistical significance. Conclusion: ChatGPT-5.2 and DeepSeek-V3.2 both generated responses that orthopedic specialists rated highly across the four evaluated domains. Neither model demonstrated statistically significant superiority. These systems may support patient education as supplementary information tools, but their outputs should remain subject to clinical verification and should not replace individualized patient-physician communication.