Comparing Artificial Intelligence Large Language Models in Medical Training: A Performance Analysis of ChatGPT and DeepSeek on United States Medical Licensing Examination (USMLE) Style Questions Article Swipe
Runze Zhang
,
Qing Cai
,
Ângela Lúcia Bagnatori Sartori
,
Nasser Gayed
,
Heather Collette
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.7759/cureus.90212
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.7759/cureus.90212
Introduction The integration of artificial intelligence (AI) into medical education is reshaping how students prepare for standardized examinations. Prior studies have shown that AI models can achieve high accuracy on United States Medical Licensing Examination (USMLE) questions, highlighting their potential for examination preparation. ChatGPT (GPT), especially the 4o model, is one of the most widely used AI models; however, its accessibility is limited by subscription costs and regional censorship. DeepSeek (DS), a newer AI model, offers free access and has demonstrated comparable performance in general tasks. In this study, we compared the performance of GPT-4o and DS DeepThink R1 on the AMBOSS medical board preparation question bank to evaluate their potential and limitations as supplementary tools in medical education. Methods We extracted 1,079 USMLE-style multiple-choice questions from the AMBOSS question bank. Questions were categorized by USMLE Step 1 and Step 2 examinations and further grouped by topic, resulting in 36 categories. Each question was assigned a difficulty level (easy, intermediate, or hard) based on AMBOSS grading criteria. To ensure balanced representation, we randomly selected 10 questions per difficulty level per category. Questions and answer choices were copied verbatim from the AMBOSS website and input into GPT-4o and DS R1 without any modification. Model responses were scored as correct or incorrect, and correctness rates were compared across GPT-4o, DS R1, and AMBOSS user performance. Results Both GPT and DS outperformed AMBOSS users, with overall accuracies of 88.79%, 78.68%, and 56.98%, respectively. Comparing GPT and DS, GPT performed significantly better overall (t=7.90, p<0.0001). When stratified by examination type, GPT achieved significantly higher accuracy than DS in both Step 1 (0.89 vs. 0.78, p < 0.0001) and Step 2 (0.88 vs. 0.80, p < 0.0001). GPT consistently showed higher accuracy than DS at all three difficulty levels. However, when further stratified by examination type, statistically significances were only observed in intermediate (p = 0.0002) and hard (p = 0.0021) questions in both Step 1 and Step 2. Conclusion Our findings demonstrated that both AI models outperformed human learners, with GPT-4o showing superior accuracy, particularly in intermediate and hard questions. While DS underperformed relative to GPT, its free accessibility and competitive accuracy in easy questions suggest that it may serve as a viable alternative, particularly in resource-limited settings.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.7759/cureus.90212
- OA Status
- diamond
- References
- 10
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4413458885
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4413458885Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.7759/cureus.90212Digital Object Identifier
- Title
-
Comparing Artificial Intelligence Large Language Models in Medical Training: A Performance Analysis of ChatGPT and DeepSeek on United States Medical Licensing Examination (USMLE) Style QuestionsWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-08-16Full publication date if available
- Authors
-
Runze Zhang, Qing Cai, Ângela Lúcia Bagnatori Sartori, Nasser Gayed, Heather ColletteList of authors in order
- Landing page
-
https://doi.org/10.7759/cureus.90212Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
diamondOpen access status per OpenAlex
- OA URL
-
https://doi.org/10.7759/cureus.90212Direct OA link when available
- Concepts
-
Medicine, United States Medical Licensing Examination, Style (visual arts), Training (meteorology), Medical education, Medical school, Artificial intelligence, Visual arts, Computer science, Meteorology, Physics, ArtTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- References (count)
-
10Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4413458885 |
|---|---|
| doi | https://doi.org/10.7759/cureus.90212 |
| ids.doi | https://doi.org/10.7759/cureus.90212 |
| ids.pmid | https://pubmed.ncbi.nlm.nih.gov/40970008 |
| ids.openalex | https://openalex.org/W4413458885 |
| fwci | 0.0 |
| type | article |
| title | Comparing Artificial Intelligence Large Language Models in Medical Training: A Performance Analysis of ChatGPT and DeepSeek on United States Medical Licensing Examination (USMLE) Style Questions |
| biblio.issue | 8 |
| biblio.volume | 17 |
| biblio.last_page | e90212 |
| biblio.first_page | e90212 |
| topics[0].id | https://openalex.org/T11636 |
| topics[0].field.id | https://openalex.org/fields/27 |
| topics[0].field.display_name | Medicine |
| topics[0].score | 0.9997000098228455 |
| topics[0].domain.id | https://openalex.org/domains/4 |
| topics[0].domain.display_name | Health Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2718 |
| topics[0].subfield.display_name | Health Informatics |
| topics[0].display_name | Artificial Intelligence in Healthcare and Education |
| topics[1].id | https://openalex.org/T12422 |
| topics[1].field.id | https://openalex.org/fields/27 |
| topics[1].field.display_name | Medicine |
| topics[1].score | 0.942799985408783 |
| topics[1].domain.id | https://openalex.org/domains/4 |
| topics[1].domain.display_name | Health Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2741 |
| topics[1].subfield.display_name | Radiology, Nuclear Medicine and Imaging |
| topics[1].display_name | Radiomics and Machine Learning in Medical Imaging |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C71924100 |
| concepts[0].level | 0 |
| concepts[0].score | 0.9011654853820801 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q11190 |
| concepts[0].display_name | Medicine |
| concepts[1].id | https://openalex.org/C2779741528 |
| concepts[1].level | 3 |
| concepts[1].score | 0.7052326202392578 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q1156524 |
| concepts[1].display_name | United States Medical Licensing Examination |
| concepts[2].id | https://openalex.org/C2776445246 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6009185910224915 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q1792644 |
| concepts[2].display_name | Style (visual arts) |
| concepts[3].id | https://openalex.org/C2777211547 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5312915444374084 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q17141490 |
| concepts[3].display_name | Training (meteorology) |
| concepts[4].id | https://openalex.org/C509550671 |
| concepts[4].level | 1 |
| concepts[4].score | 0.5238064527511597 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q126945 |
| concepts[4].display_name | Medical education |
| concepts[5].id | https://openalex.org/C2993838110 |
| concepts[5].level | 2 |
| concepts[5].score | 0.36653995513916016 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q494230 |
| concepts[5].display_name | Medical school |
| concepts[6].id | https://openalex.org/C154945302 |
| concepts[6].level | 1 |
| concepts[6].score | 0.3370017409324646 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[6].display_name | Artificial intelligence |
| concepts[7].id | https://openalex.org/C153349607 |
| concepts[7].level | 1 |
| concepts[7].score | 0.055229365825653076 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q36649 |
| concepts[7].display_name | Visual arts |
| concepts[8].id | https://openalex.org/C41008148 |
| concepts[8].level | 0 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[8].display_name | Computer science |
| concepts[9].id | https://openalex.org/C153294291 |
| concepts[9].level | 1 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q25261 |
| concepts[9].display_name | Meteorology |
| concepts[10].id | https://openalex.org/C121332964 |
| concepts[10].level | 0 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[10].display_name | Physics |
| concepts[11].id | https://openalex.org/C142362112 |
| concepts[11].level | 0 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q735 |
| concepts[11].display_name | Art |
| keywords[0].id | https://openalex.org/keywords/medicine |
| keywords[0].score | 0.9011654853820801 |
| keywords[0].display_name | Medicine |
| keywords[1].id | https://openalex.org/keywords/united-states-medical-licensing-examination |
| keywords[1].score | 0.7052326202392578 |
| keywords[1].display_name | United States Medical Licensing Examination |
| keywords[2].id | https://openalex.org/keywords/style |
| keywords[2].score | 0.6009185910224915 |
| keywords[2].display_name | Style (visual arts) |
| keywords[3].id | https://openalex.org/keywords/training |
| keywords[3].score | 0.5312915444374084 |
| keywords[3].display_name | Training (meteorology) |
| keywords[4].id | https://openalex.org/keywords/medical-education |
| keywords[4].score | 0.5238064527511597 |
| keywords[4].display_name | Medical education |
| keywords[5].id | https://openalex.org/keywords/medical-school |
| keywords[5].score | 0.36653995513916016 |
| keywords[5].display_name | Medical school |
| keywords[6].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[6].score | 0.3370017409324646 |
| keywords[6].display_name | Artificial intelligence |
| keywords[7].id | https://openalex.org/keywords/visual-arts |
| keywords[7].score | 0.055229365825653076 |
| keywords[7].display_name | Visual arts |
| language | en |
| locations[0].id | doi:10.7759/cureus.90212 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S2738950867 |
| locations[0].source.issn | 2168-8184 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | 2168-8184 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Cureus |
| locations[0].source.host_organization | https://openalex.org/P4310316779 |
| locations[0].source.host_organization_name | Cureus, Inc. |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310316779 |
| locations[0].source.host_organization_lineage_names | Cureus, Inc. |
| locations[0].license | |
| locations[0].pdf_url | |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Cureus |
| locations[0].landing_page_url | https://doi.org/10.7759/cureus.90212 |
| locations[1].id | pmid:40970008 |
| locations[1].is_oa | False |
| locations[1].source.id | https://openalex.org/S4306525036 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | False |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | PubMed |
| locations[1].source.host_organization | https://openalex.org/I1299303238 |
| locations[1].source.host_organization_name | National Institutes of Health |
| locations[1].source.host_organization_lineage | https://openalex.org/I1299303238 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | publishedVersion |
| locations[1].raw_type | |
| locations[1].license_id | |
| locations[1].is_accepted | True |
| locations[1].is_published | True |
| locations[1].raw_source_name | Cureus |
| locations[1].landing_page_url | https://pubmed.ncbi.nlm.nih.gov/40970008 |
| locations[2].id | pmh:oai:europepmc.org:11252101 |
| locations[2].is_oa | True |
| locations[2].source.id | https://openalex.org/S4306400806 |
| locations[2].source.issn | |
| locations[2].source.type | repository |
| locations[2].source.is_oa | False |
| locations[2].source.issn_l | |
| locations[2].source.is_core | False |
| locations[2].source.is_in_doaj | False |
| locations[2].source.display_name | Europe PMC (PubMed Central) |
| locations[2].source.host_organization | https://openalex.org/I1303153112 |
| locations[2].source.host_organization_name | European Bioinformatics Institute |
| locations[2].source.host_organization_lineage | https://openalex.org/I1303153112 |
| locations[2].license | other-oa |
| locations[2].pdf_url | |
| locations[2].version | submittedVersion |
| locations[2].raw_type | Text |
| locations[2].license_id | https://openalex.org/licenses/other-oa |
| locations[2].is_accepted | False |
| locations[2].is_published | False |
| locations[2].raw_source_name | |
| locations[2].landing_page_url | https://www.ncbi.nlm.nih.gov/pmc/articles/12442328 |
| indexed_in | crossref, pubmed |
| authorships[0].author.id | https://openalex.org/A5101549172 |
| authorships[0].author.orcid | https://orcid.org/0009-0003-6318-3342 |
| authorships[0].author.display_name | Runze Zhang |
| authorships[0].countries | US |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I39422238 |
| authorships[0].affiliations[0].raw_affiliation_string | Department of Medicine, College of Medicine, University of Illinois at Chicago, Chicago, USA. |
| authorships[0].institutions[0].id | https://openalex.org/I39422238 |
| authorships[0].institutions[0].ror | https://ror.org/02mpq6x41 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I39422238 |
| authorships[0].institutions[0].country_code | US |
| authorships[0].institutions[0].display_name | University of Illinois Chicago |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Runze Zhang |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Department of Medicine, College of Medicine, University of Illinois at Chicago, Chicago, USA. |
| authorships[1].author.id | https://openalex.org/A5001193929 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-2157-396X |
| authorships[1].author.display_name | Qing Cai |
| authorships[1].countries | US |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I16820183 |
| authorships[1].affiliations[0].raw_affiliation_string | Department of Medicine, Carle Illinois College of Medicine, Urbana, USA. |
| authorships[1].institutions[0].id | https://openalex.org/I16820183 |
| authorships[1].institutions[0].ror | https://ror.org/02ys5x139 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I16820183 |
| authorships[1].institutions[0].country_code | US |
| authorships[1].institutions[0].display_name | Illinois College |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Qinyun Cai |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Department of Medicine, Carle Illinois College of Medicine, Urbana, USA. |
| authorships[2].author.id | https://openalex.org/A5008938980 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-5911-8797 |
| authorships[2].author.display_name | Ângela Lúcia Bagnatori Sartori |
| authorships[2].countries | US |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I189273616 |
| authorships[2].affiliations[0].raw_affiliation_string | Department of Medicine, Chicago Medical School, Rosalind Franklin University of Medicine and Science, North Chicago, USA. |
| authorships[2].institutions[0].id | https://openalex.org/I189273616 |
| authorships[2].institutions[0].ror | https://ror.org/04fegvg32 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I189273616 |
| authorships[2].institutions[0].country_code | US |
| authorships[2].institutions[0].display_name | Rosalind Franklin University of Medicine and Science |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Amanda Sartori |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Department of Medicine, Chicago Medical School, Rosalind Franklin University of Medicine and Science, North Chicago, USA. |
| authorships[3].author.id | https://openalex.org/A5097171290 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Nasser Gayed |
| authorships[3].countries | US |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I16820183 |
| authorships[3].affiliations[0].raw_affiliation_string | Department of Biomedical and Translational Science, Carle Illinois College of Medicine, Urbana, USA. |
| authorships[3].institutions[0].id | https://openalex.org/I16820183 |
| authorships[3].institutions[0].ror | https://ror.org/02ys5x139 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I16820183 |
| authorships[3].institutions[0].country_code | US |
| authorships[3].institutions[0].display_name | Illinois College |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Nasser Gayed |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Department of Biomedical and Translational Science, Carle Illinois College of Medicine, Urbana, USA. |
| authorships[4].author.id | https://openalex.org/A5119400278 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Heather Collette |
| authorships[4].countries | US |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I32971472 |
| authorships[4].affiliations[0].raw_affiliation_string | Department of Pediatrics, Yale School of Medicine, New Haven, USA. |
| authorships[4].institutions[0].id | https://openalex.org/I32971472 |
| authorships[4].institutions[0].ror | https://ror.org/03v76x132 |
| authorships[4].institutions[0].type | education |
| authorships[4].institutions[0].lineage | https://openalex.org/I32971472 |
| authorships[4].institutions[0].country_code | US |
| authorships[4].institutions[0].display_name | Yale University |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Heather Collette |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | Department of Pediatrics, Yale School of Medicine, New Haven, USA. |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://doi.org/10.7759/cureus.90212 |
| open_access.oa_status | diamond |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Comparing Artificial Intelligence Large Language Models in Medical Training: A Performance Analysis of ChatGPT and DeepSeek on United States Medical Licensing Examination (USMLE) Style Questions |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T11636 |
| primary_topic.field.id | https://openalex.org/fields/27 |
| primary_topic.field.display_name | Medicine |
| primary_topic.score | 0.9997000098228455 |
| primary_topic.domain.id | https://openalex.org/domains/4 |
| primary_topic.domain.display_name | Health Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2718 |
| primary_topic.subfield.display_name | Health Informatics |
| primary_topic.display_name | Artificial Intelligence in Healthcare and Education |
| related_works | https://openalex.org/W230091440, https://openalex.org/W2416519807, https://openalex.org/W2776799857, https://openalex.org/W2011175823, https://openalex.org/W3037189781, https://openalex.org/W4243413683, https://openalex.org/W2470050756, https://openalex.org/W1998275520, https://openalex.org/W2151193840, https://openalex.org/W2462672465 |
| cited_by_count | 0 |
| locations_count | 3 |
| best_oa_location.id | doi:10.7759/cureus.90212 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S2738950867 |
| best_oa_location.source.issn | 2168-8184 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | 2168-8184 |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Cureus |
| best_oa_location.source.host_organization | https://openalex.org/P4310316779 |
| best_oa_location.source.host_organization_name | Cureus, Inc. |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310316779 |
| best_oa_location.source.host_organization_lineage_names | Cureus, Inc. |
| best_oa_location.license | |
| best_oa_location.pdf_url | |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Cureus |
| best_oa_location.landing_page_url | https://doi.org/10.7759/cureus.90212 |
| primary_location.id | doi:10.7759/cureus.90212 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S2738950867 |
| primary_location.source.issn | 2168-8184 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | 2168-8184 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Cureus |
| primary_location.source.host_organization | https://openalex.org/P4310316779 |
| primary_location.source.host_organization_name | Cureus, Inc. |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310316779 |
| primary_location.source.host_organization_lineage_names | Cureus, Inc. |
| primary_location.license | |
| primary_location.pdf_url | |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Cureus |
| primary_location.landing_page_url | https://doi.org/10.7759/cureus.90212 |
| publication_date | 2025-08-16 |
| publication_year | 2025 |
| referenced_works | https://openalex.org/W4392769984, https://openalex.org/W4384695580, https://openalex.org/W4405735651, https://openalex.org/W4319662928, https://openalex.org/W4404134492, https://openalex.org/W4401046213, https://openalex.org/W3035286874, https://openalex.org/W4319460874, https://openalex.org/W4387653139, https://openalex.org/W4399568952 |
| referenced_works_count | 10 |
| abstract_inverted_index.1 | 137, 266, 320 |
| abstract_inverted_index.2 | 140, 275 |
| abstract_inverted_index.< | 271, 280 |
| abstract_inverted_index.= | 309, 314 |
| abstract_inverted_index.a | 71, 155, 367 |
| abstract_inverted_index.p | 270, 279 |
| abstract_inverted_index.(p | 308, 313 |
| abstract_inverted_index.10 | 174 |
| abstract_inverted_index.2. | 323 |
| abstract_inverted_index.36 | 149 |
| abstract_inverted_index.4o | 47 |
| abstract_inverted_index.AI | 23, 56, 73, 330 |
| abstract_inverted_index.DS | 96, 197, 217, 227, 262, 288, 347 |
| abstract_inverted_index.In | 86 |
| abstract_inverted_index.R1 | 98, 198 |
| abstract_inverted_index.To | 167 |
| abstract_inverted_index.We | 120 |
| abstract_inverted_index.as | 113, 206, 366 |
| abstract_inverted_index.at | 289 |
| abstract_inverted_index.by | 63, 134, 145, 253, 298 |
| abstract_inverted_index.in | 83, 116, 148, 263, 306, 317, 341, 358, 371 |
| abstract_inverted_index.is | 10, 49, 61 |
| abstract_inverted_index.it | 363 |
| abstract_inverted_index.of | 3, 51, 93, 234 |
| abstract_inverted_index.on | 29, 99, 163 |
| abstract_inverted_index.or | 160, 208 |
| abstract_inverted_index.to | 107, 350 |
| abstract_inverted_index.we | 89, 171 |
| abstract_inverted_index.DS, | 243 |
| abstract_inverted_index.GPT | 225, 241, 244, 256, 282 |
| abstract_inverted_index.Our | 325 |
| abstract_inverted_index.R1, | 218 |
| abstract_inverted_index.The | 1 |
| abstract_inverted_index.all | 290 |
| abstract_inverted_index.and | 66, 78, 95, 111, 138, 142, 182, 192, 196, 210, 219, 226, 237, 242, 273, 311, 321, 343, 355 |
| abstract_inverted_index.any | 200 |
| abstract_inverted_index.can | 25 |
| abstract_inverted_index.for | 15, 40 |
| abstract_inverted_index.has | 79 |
| abstract_inverted_index.how | 12 |
| abstract_inverted_index.its | 59, 352 |
| abstract_inverted_index.may | 364 |
| abstract_inverted_index.one | 50 |
| abstract_inverted_index.per | 176, 179 |
| abstract_inverted_index.the | 46, 52, 91, 100, 127, 189 |
| abstract_inverted_index.vs. | 268, 277 |
| abstract_inverted_index.was | 153 |
| abstract_inverted_index.(AI) | 6 |
| abstract_inverted_index.Both | 224 |
| abstract_inverted_index.Each | 151 |
| abstract_inverted_index.GPT, | 351 |
| abstract_inverted_index.Step | 136, 139, 265, 274, 319, 322 |
| abstract_inverted_index.When | 251 |
| abstract_inverted_index.bank | 106 |
| abstract_inverted_index.both | 264, 318, 329 |
| abstract_inverted_index.easy | 359 |
| abstract_inverted_index.free | 76, 353 |
| abstract_inverted_index.from | 126, 188 |
| abstract_inverted_index.hard | 312, 344 |
| abstract_inverted_index.have | 20 |
| abstract_inverted_index.high | 27 |
| abstract_inverted_index.into | 7, 194 |
| abstract_inverted_index.most | 53 |
| abstract_inverted_index.only | 304 |
| abstract_inverted_index.than | 261, 287 |
| abstract_inverted_index.that | 22, 328, 362 |
| abstract_inverted_index.this | 87 |
| abstract_inverted_index.used | 55 |
| abstract_inverted_index.user | 221 |
| abstract_inverted_index.were | 132, 185, 204, 213, 303 |
| abstract_inverted_index.when | 295 |
| abstract_inverted_index.with | 231, 335 |
| abstract_inverted_index.(0.88 | 276 |
| abstract_inverted_index.(0.89 | 267 |
| abstract_inverted_index.(DS), | 70 |
| abstract_inverted_index.0.78, | 269 |
| abstract_inverted_index.0.80, | 278 |
| abstract_inverted_index.1,079 | 122 |
| abstract_inverted_index.Model | 202 |
| abstract_inverted_index.Prior | 18 |
| abstract_inverted_index.USMLE | 135 |
| abstract_inverted_index.While | 346 |
| abstract_inverted_index.bank. | 130 |
| abstract_inverted_index.based | 162 |
| abstract_inverted_index.board | 103 |
| abstract_inverted_index.costs | 65 |
| abstract_inverted_index.hard) | 161 |
| abstract_inverted_index.human | 333 |
| abstract_inverted_index.input | 193 |
| abstract_inverted_index.level | 157, 178 |
| abstract_inverted_index.newer | 72 |
| abstract_inverted_index.rates | 212 |
| abstract_inverted_index.serve | 365 |
| abstract_inverted_index.shown | 21 |
| abstract_inverted_index.their | 38, 109 |
| abstract_inverted_index.three | 291 |
| abstract_inverted_index.tools | 115 |
| abstract_inverted_index.type, | 255, 300 |
| abstract_inverted_index.(GPT), | 44 |
| abstract_inverted_index.(easy, | 158 |
| abstract_inverted_index.AMBOSS | 101, 128, 164, 190, 220, 229 |
| abstract_inverted_index.GPT-4o | 94, 195, 336 |
| abstract_inverted_index.States | 31 |
| abstract_inverted_index.United | 30 |
| abstract_inverted_index.access | 77 |
| abstract_inverted_index.across | 215 |
| abstract_inverted_index.answer | 183 |
| abstract_inverted_index.better | 247 |
| abstract_inverted_index.copied | 186 |
| abstract_inverted_index.ensure | 168 |
| abstract_inverted_index.higher | 259, 285 |
| abstract_inverted_index.model, | 48, 74 |
| abstract_inverted_index.models | 24, 331 |
| abstract_inverted_index.offers | 75 |
| abstract_inverted_index.scored | 205 |
| abstract_inverted_index.showed | 284 |
| abstract_inverted_index.study, | 88 |
| abstract_inverted_index.tasks. | 85 |
| abstract_inverted_index.topic, | 146 |
| abstract_inverted_index.users, | 230 |
| abstract_inverted_index.viable | 368 |
| abstract_inverted_index.widely | 54 |
| abstract_inverted_index.(USMLE) | 35 |
| abstract_inverted_index.0.0001) | 272 |
| abstract_inverted_index.0.0002) | 310 |
| abstract_inverted_index.0.0021) | 315 |
| abstract_inverted_index.56.98%, | 238 |
| abstract_inverted_index.78.68%, | 236 |
| abstract_inverted_index.88.79%, | 235 |
| abstract_inverted_index.ChatGPT | 43 |
| abstract_inverted_index.GPT-4o, | 216 |
| abstract_inverted_index.Medical | 32 |
| abstract_inverted_index.Methods | 119 |
| abstract_inverted_index.Results | 223 |
| abstract_inverted_index.achieve | 26 |
| abstract_inverted_index.choices | 184 |
| abstract_inverted_index.correct | 207 |
| abstract_inverted_index.further | 143, 296 |
| abstract_inverted_index.general | 84 |
| abstract_inverted_index.grading | 165 |
| abstract_inverted_index.grouped | 144 |
| abstract_inverted_index.levels. | 293 |
| abstract_inverted_index.limited | 62 |
| abstract_inverted_index.medical | 8, 102, 117 |
| abstract_inverted_index.models; | 57 |
| abstract_inverted_index.overall | 232, 248 |
| abstract_inverted_index.prepare | 14 |
| abstract_inverted_index.showing | 337 |
| abstract_inverted_index.studies | 19 |
| abstract_inverted_index.suggest | 361 |
| abstract_inverted_index.website | 191 |
| abstract_inverted_index.without | 199 |
| abstract_inverted_index.(t=7.90, | 249 |
| abstract_inverted_index.0.0001). | 281 |
| abstract_inverted_index.DeepSeek | 69 |
| abstract_inverted_index.However, | 294 |
| abstract_inverted_index.accuracy | 28, 260, 286, 357 |
| abstract_inverted_index.achieved | 257 |
| abstract_inverted_index.assigned | 154 |
| abstract_inverted_index.balanced | 169 |
| abstract_inverted_index.compared | 90, 214 |
| abstract_inverted_index.evaluate | 108 |
| abstract_inverted_index.findings | 326 |
| abstract_inverted_index.however, | 58 |
| abstract_inverted_index.observed | 305 |
| abstract_inverted_index.question | 105, 129, 152 |
| abstract_inverted_index.randomly | 172 |
| abstract_inverted_index.regional | 67 |
| abstract_inverted_index.relative | 349 |
| abstract_inverted_index.selected | 173 |
| abstract_inverted_index.students | 13 |
| abstract_inverted_index.superior | 338 |
| abstract_inverted_index.verbatim | 187 |
| abstract_inverted_index.Comparing | 240 |
| abstract_inverted_index.DeepThink | 97 |
| abstract_inverted_index.Licensing | 33 |
| abstract_inverted_index.Questions | 131, 181 |
| abstract_inverted_index.accuracy, | 339 |
| abstract_inverted_index.category. | 180 |
| abstract_inverted_index.criteria. | 166 |
| abstract_inverted_index.education | 9 |
| abstract_inverted_index.extracted | 121 |
| abstract_inverted_index.learners, | 334 |
| abstract_inverted_index.performed | 245 |
| abstract_inverted_index.potential | 39, 110 |
| abstract_inverted_index.questions | 125, 175, 316, 360 |
| abstract_inverted_index.reshaping | 11 |
| abstract_inverted_index.responses | 203 |
| abstract_inverted_index.resulting | 147 |
| abstract_inverted_index.settings. | 373 |
| abstract_inverted_index.Conclusion | 324 |
| abstract_inverted_index.accuracies | 233 |
| abstract_inverted_index.artificial | 4 |
| abstract_inverted_index.comparable | 81 |
| abstract_inverted_index.difficulty | 156, 177, 292 |
| abstract_inverted_index.education. | 118 |
| abstract_inverted_index.especially | 45 |
| abstract_inverted_index.incorrect, | 209 |
| abstract_inverted_index.p<0.0001). | 250 |
| abstract_inverted_index.questions, | 36 |
| abstract_inverted_index.questions. | 345 |
| abstract_inverted_index.stratified | 252, 297 |
| abstract_inverted_index.Examination | 34 |
| abstract_inverted_index.USMLE-style | 123 |
| abstract_inverted_index.categories. | 150 |
| abstract_inverted_index.categorized | 133 |
| abstract_inverted_index.censorship. | 68 |
| abstract_inverted_index.competitive | 356 |
| abstract_inverted_index.correctness | 211 |
| abstract_inverted_index.examination | 41, 254, 299 |
| abstract_inverted_index.integration | 2 |
| abstract_inverted_index.limitations | 112 |
| abstract_inverted_index.performance | 82, 92 |
| abstract_inverted_index.preparation | 104 |
| abstract_inverted_index.Introduction | 0 |
| abstract_inverted_index.alternative, | 369 |
| abstract_inverted_index.consistently | 283 |
| abstract_inverted_index.demonstrated | 80, 327 |
| abstract_inverted_index.examinations | 141 |
| abstract_inverted_index.highlighting | 37 |
| abstract_inverted_index.intelligence | 5 |
| abstract_inverted_index.intermediate | 307, 342 |
| abstract_inverted_index.outperformed | 228, 332 |
| abstract_inverted_index.particularly | 340, 370 |
| abstract_inverted_index.performance. | 222 |
| abstract_inverted_index.preparation. | 42 |
| abstract_inverted_index.standardized | 16 |
| abstract_inverted_index.subscription | 64 |
| abstract_inverted_index.accessibility | 60, 354 |
| abstract_inverted_index.examinations. | 17 |
| abstract_inverted_index.intermediate, | 159 |
| abstract_inverted_index.modification. | 201 |
| abstract_inverted_index.respectively. | 239 |
| abstract_inverted_index.significances | 302 |
| abstract_inverted_index.significantly | 246, 258 |
| abstract_inverted_index.statistically | 301 |
| abstract_inverted_index.supplementary | 114 |
| abstract_inverted_index.underperformed | 348 |
| abstract_inverted_index.multiple-choice | 124 |
| abstract_inverted_index.representation, | 170 |
| abstract_inverted_index.resource-limited | 372 |
| cited_by_percentile_year | |
| countries_distinct_count | 1 |
| institutions_distinct_count | 5 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.4699999988079071 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile.value | 0.31898954 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |