{"doi":"10.1038/s41598-025-08601-2","title":"A comparative analysis of DeepSeek R1, DeepSeek-R1-Lite, OpenAi o1 Pro, and Grok 3 performance on ophthalmology board-style questions","abstract":"The ability of large language models (LLMs) to accurately answer medical board-style questions reflects their potential to benefit medical education and real-time clinical decision-making. With the recent advance to reasoning models, the latest LLMs excel at addressing complex problems in benchmark math and science tests. This study assessed the performance of first-generation reasoning models-DeepSeek's R1 and R1-Lite, OpenAI's o1 Pro, and Grok 3-on 493 ophthalmology questions sourced from the StatPearls and EyeQuiz question banks. o1 Pro achieved the highest overall accuracy (83.4%), significantly outperforming DeepSeek R1 (72.5%), DeepSeek-R1-Lite (76.5%), and Grok 3 (69.2%) (p < 0.001 for all pairwise comparisons). o1 Pro also demonstrated superior performance in questions from eight of nine ophthalmologic subfields, questions of second and third order cognitive complexity, and on image-based questions. DeepSeek-R1-Lite performed the second best, despite relatively small memory requirements, while Grok 3 performed inferiorly overall. These findings demonstrate that the strong performance of the first-generation reasoning models extends beyond benchmark tests to high-complexity ophthalmology questions. While these findings suggest a potential role for reasoning models in medical education and clinical practice, further research is needed to understand their performance with real-world data, their integration into educational and clinical settings, and human-AI interactions.","journal":"Scientific Reports","year":2025,"id":510846,"datarank":0.4493598410330987,"base_score":2.995732273553991,"endowment":2.995732273553991,"self_citation_contribution":0.4493598410330987,"citation_network_contribution":0.0,"self_endowment_contribution":0.4493598410330987,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":19,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9606,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2025-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1368585,"name":"Tathya Shah","orcid":null,"position":1,"is_corresponding":false},{"id":1368586,"name":"Aditya Pandiarajan","orcid":null,"position":2,"is_corresponding":false},{"id":1368016,"name":"Alan Tang","orcid":"0000-0001-5744-3628","position":3,"is_corresponding":false},{"id":775060,"name":"Kyle Bolo","orcid":"0000-0001-7885-192X","position":4,"is_corresponding":false},{"id":960426,"name":"Văn Thành Nguyễn","orcid":"0000-0002-2534-5465","position":5,"is_corresponding":false},{"id":339514,"name":"Benjamin Y. Xu","orcid":"0000-0003-1573-988X","position":6,"is_corresponding":false},{"id":1368015,"name":"Ryan Shean","orcid":"0000-0002-2831-8040","position":0,"is_corresponding":true}],"reference_count":30,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-07-19T02:47:50.575618Z","pmid":"40595291","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}