Published on in Vol 9 (2023)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/45312, first published .
How Does ChatGPT Perform on the United States Medical Licensing Examination (USMLE)? The Implications of Large Language Models for Medical Education and Knowledge Assessment

How Does ChatGPT Perform on the United States Medical Licensing Examination (USMLE)? The Implications of Large Language Models for Medical Education and Knowledge Assessment

How Does ChatGPT Perform on the United States Medical Licensing Examination (USMLE)? The Implications of Large Language Models for Medical Education and Knowledge Assessment

New in JMIR MedEdu: How Does ChatGPT Perform on the United States Medical Licensing Examination? The Implications o… https://t.co/4ivUXAWjBA

3:14 PM · Feb 08, 2023

3
1

RT @jmirpub: New in JMIR MedEdu: How Does ChatGPT Perform on the United States Medical Licensing Examination? The Implications of Large Lan…

3:14 PM · Feb 08, 2023

3
1

Performance of #chatgpt on #usmle and implications for #meded. Potential applications for small group education an… https://t.co/iuvZYfFRha

3:36 PM · Feb 08, 2023

0
0

How Does ChatGPT Perform on the United States Medical Licensing Examination? The Implications of Large Language Mod… https://t.co/nQQT0z5nJM

6:11 PM · Feb 08, 2023

0
0

#NLP "How Does ChatGPT Perform on the United States Medical Licensing Examination? The Implications of Large Langua… https://t.co/Se9oKOJjeo

6:20 PM · Feb 08, 2023

0
0

RT @EM_Informatics: Performance of #chatgpt on #usmle and implications for #meded. Potential applications for small group education and AI…

2:14 PM · Feb 09, 2023

1
1

There's a technical term for that: "hallucination." The ChatGPT model that passed the USMLE gave logical-but-incor… https://t.co/SttbwZY2sx

6:59 PM · Feb 13, 2023

33
9

RT @MaxKennerly: There's a technical term for that: "hallucination." The ChatGPT model that passed the USMLE gave logical-but-incorrect an…

7:01 PM · Feb 13, 2023

33
9

RT @MaxKennerly: There's a technical term for that: "hallucination." The ChatGPT model that passed the USMLE gave logical-but-incorrect an…

7:03 PM · Feb 13, 2023

33
9

RT @MaxKennerly: There's a technical term for that: "hallucination." The ChatGPT model that passed the USMLE gave logical-but-incorrect an…

7:05 PM · Feb 13, 2023

33
9

RT @MaxKennerly: There's a technical term for that: "hallucination." The ChatGPT model that passed the USMLE gave logical-but-incorrect an…

7:09 PM · Feb 13, 2023

33
9

RT @MaxKennerly: There's a technical term for that: "hallucination." The ChatGPT model that passed the USMLE gave logical-but-incorrect an…

7:12 PM · Feb 13, 2023

33
9

RT @MaxKennerly: There's a technical term for that: "hallucination." The ChatGPT model that passed the USMLE gave logical-but-incorrect an…

7:17 PM · Feb 13, 2023

33
9

RT @MaxKennerly: There's a technical term for that: "hallucination." The ChatGPT model that passed the USMLE gave logical-but-incorrect an…

8:53 PM · Feb 13, 2023

33
9

RT @MaxKennerly: There's a technical term for that: "hallucination." The ChatGPT model that passed the USMLE gave logical-but-incorrect an…

4:39 PM · Feb 14, 2023

58
17

RT @MaxKennerly: There's a technical term for that: "hallucination." The ChatGPT model that passed the USMLE gave logical-but-incorrect an…

4:48 PM · Feb 14, 2023

58
17

RT @MaxKennerly: There's a technical term for that: "hallucination." The ChatGPT model that passed the USMLE gave logical-but-incorrect an…

5:07 PM · Feb 14, 2023

58
17

RT @MaxKennerly: There's a technical term for that: "hallucination." The ChatGPT model that passed the USMLE gave logical-but-incorrect an…

5:40 PM · Feb 14, 2023

58
17

RT @MaxKennerly: There's a technical term for that: "hallucination." The ChatGPT model that passed the USMLE gave logical-but-incorrect an…

5:40 PM · Feb 14, 2023

58
17

RT @MaxKennerly: There's a technical term for that: "hallucination." The ChatGPT model that passed the USMLE gave logical-but-incorrect an…

5:49 PM · Feb 14, 2023

58
17

RT @MaxKennerly: There's a technical term for that: "hallucination." The ChatGPT model that passed the USMLE gave logical-but-incorrect an…

6:02 PM · Feb 14, 2023

58
17

RT @MaxKennerly: There's a technical term for that: "hallucination." The ChatGPT model that passed the USMLE gave logical-but-incorrect an…

9:04 PM · Feb 14, 2023

58
17

ほー。 Check out this fascinating article https://t.co/wehfB83dnr

9:12 AM · Feb 19, 2023

0
0

How does ChatGPT Perform on the United States Medical Licensing Examination? @sonu_monika @bimedotcomhttps://t.co/n7fa4cqJ4O

1:11 PM · Feb 21, 2023

6
4

RT @EstelaMandela: How does ChatGPT Perform on the United States Medical Licensing Examination? @sonu_monika @bimedotcom @tobiaskintzel @Cu…

1:16 PM · Feb 21, 2023

6
4

RT @EstelaMandela: How does ChatGPT Perform on the United States Medical Licensing Examination? @sonu_monika @bimedotcom @tobiaskintzel @Cu…

1:32 PM · Feb 21, 2023

6
4

RT @EstelaMandela: How does ChatGPT Perform on the United States Medical Licensing Examination? @sonu_monika @bimedotcom @tobiaskintzel @Cu…

2:12 PM · Feb 21, 2023

6
4

RT @EstelaMandela: How does ChatGPT Perform on the United States Medical Licensing Examination? @sonu_monika @bimedotcom @tobiaskintzel @Cu…

7:11 PM · Feb 21, 2023

6
4

RT @EstelaMandela: How does ChatGPT Perform on the United States Medical Licensing Examination? @sonu_monika @bimedotcom @tobiaskintzel @Cu…

2:35 AM · Feb 22, 2023

11
9

RT @EstelaMandela: How does ChatGPT Perform on the United States Medical Licensing Examination? @sonu_monika @bimedotcom @tobiaskintzel @Cu…

3:16 AM · Feb 22, 2023

11
9

RT @EstelaMandela: How does ChatGPT Perform on the United States Medical Licensing Examination? @sonu_monika @bimedotcom @tobiaskintzel @Cu…

10:09 AM · Feb 22, 2023

11
9

RT @EstelaMandela: How does ChatGPT Perform on the United States Medical Licensing Examination? @sonu_monika @bimedotcom @tobiaskintzel @Cu…

10:51 AM · Feb 22, 2023

11
9

RT @EstelaMandela: How does ChatGPT Perform on the United States Medical Licensing Examination? @sonu_monika @bimedotcom @tobiaskintzel @Cu…

7:53 PM · Feb 22, 2023

11
9

Our lab recently published a paper on ChatGPT's perf on Medical Licensing Exams: namely USMLE and AMBOSS (practice… https://t.co/8nHSDcuufA

3:46 AM · Feb 23, 2023

0
0

RT @EM_Informatics: Performance of #chatgpt on #usmle and implications for #meded. Potential applications for small group education and AI…

3:45 PM · Feb 23, 2023

2
2

How Does #ChatGPT Perform on the United States Medical Licensing Examination? The Implications of Large Language Mo… https://t.co/HbS1ajBQxH

3:47 PM · Feb 23, 2023

1
0

How Does ChatGPT Perform on the United States Medical Licensing Examination? The Implications of Large Language Mod… https://t.co/hlDh6kKsmj

8:56 PM · Feb 27, 2023

0
0

RT @EM_Informatics: Performance of #chatgpt on #usmle and implications for #meded. Potential applications for small group education and AI…

5:56 PM · Feb 28, 2023

3
3

RT @jmirpub: New in JMIR MedEdu: How Does ChatGPT Perform on the United States Medical Licensing Examination? The Implications of Large Lan…

8:58 PM · Mar 07, 2023

20
8

RT @jmirpub: New in JMIR MedEdu: How Does ChatGPT Perform on the United States Medical Licensing Examination? The Implications of Large Lan…

10:14 PM · Mar 07, 2023

20
8

RT @jmirpub: New in JMIR MedEdu: How Does ChatGPT Perform on the United States Medical Licensing Examination? The Implications of Large Lan…

10:54 PM · Mar 07, 2023

20
8

RT @jmirpub: New in JMIR MedEdu: How Does ChatGPT Perform on the United States Medical Licensing Examination? The Implications of Large Lan…

11:19 PM · Mar 07, 2023

20
8

RT @jmirpub: New in JMIR MedEdu: How Does ChatGPT Perform on the United States Medical Licensing Examination? The Implications of Large Lan…

11:33 PM · Mar 07, 2023

20
8

RT @jmirpub: New in JMIR MedEdu: How Does ChatGPT Perform on the United States Medical Licensing Examination? The Implications of Large Lan…

12:48 AM · Mar 08, 2023

38
11

RT @jmirpub: New in JMIR MedEdu: How Does ChatGPT Perform on the United States Medical Licensing Examination? The Implications of Large Lan…

2:25 AM · Mar 08, 2023

38
11

#TargetedIndividuals look at the points they attack???????? https://t.co/qO8JaR86gi

4:53 AM · Mar 08, 2023

0
0

RT @jmirpub: New in JMIR MedEdu: How Does ChatGPT Perform on the United States Medical Licensing Examination? The Implications of Large Lan…

7:00 AM · Mar 08, 2023

38
11

RT @jmirpub: New in JMIR MedEdu: How Does ChatGPT Perform on the United States Medical Licensing Examination? The Implications of Large Lan…

9:17 AM · Mar 08, 2023

38
11

Check out this fascinating article https://t.co/cHpW2efPqq

8:10 AM · Mar 18, 2023

0
0

"How Does ChatGPT Perform on the United States Medical Licensing Examination? The Implications of Large Language Mo… https://t.co/Dbu0ObGIqe

4:43 PM · Mar 23, 2023

0
0

Interview: How does ChatGPT perform on the United States Medical Licensing Examination? https://t.co/V5xLo2PGNX https://t.co/3idVGr5a1T

8:00 PM · Mar 30, 2023

0
0

Our paper is out in JMIR! Other #ChatGPT x Med applications in the works, stay tuned!! https://t.co/qXk9awCVZQ

6:57 PM · Apr 14, 2023

4
0

How Does ChatGPT Perform on the United States Medical Licensing Examination? The Implications of Large Language M… https://t.co/S6XnpBSg3I

8:27 AM · May 08, 2023

0
0

Desempeño de ChatGPT en un examen de medicina de EUA. Check out this fascinating article https://t.co/pJroEJFxaL

1:44 PM · May 24, 2023

1
0

@DrHelenOram So far from the med ed world I've only seen high stakes summative exams attempted by ChatGPT, e.g. this paper, which I imagine are usually supervised in ways that wouldn't allow these tools https://t.co/6pcDdPsCtO

4:07 PM · May 30, 2023

0
0

By performing at a greater than 60% threshold on the NBME-Free-Step-1 data set, we show that the model achieves the equivalent of a passing score for a third-year medical student.  Human Doctors will be unemployed by GPT-6. ???? https://t.co/RGtObMC201

2:46 PM · Nov 29, 2023

0
0

By performing at a greater than 60% threshold on the NBME-Free-Step-1 data set, we show that the model achieves the equivalent of a passing score for a third-year medical student.  Human Doctors will be unemployed by GPT-6. ???? https://t.co/R6kTz89xVW

7:46 PM · Dec 03, 2023

1
0

Check out our most tweeted article of 2023 in JMIR Medical Education.???? We’d like to congratulate all authors involved and thank you for contributing to a successful year at JMIR Publications! https://t.co/FYqsiy0du7 @UCDMedicine @YaleMed #bestof2023 #AcademicTwitter https://t.co/3X7da55AsX

4:58 PM · Dec 20, 2023

1
0

Congrats Dr David Chartash and team ???????????? https://t.co/o75b0ApFb6

7:33 AM · Dec 21, 2023

2
1

Check out our most cited article of 2023 in JMIR Medical Education.???? We’d like to congratulate all authors involved and thank you for contributing to a successful year at JMIR Publications! https://t.co/ixw6oYNyUF @YaleMed #bestof2023 #AcademicTwitter https://t.co/QQ1zCR02gk

7:33 PM · Dec 21, 2023

0
0

RT @UCDMedicine: Congrats Dr David Chartash and team ????????????

5:11 PM · Jan 08, 2024

2
1

Where we're at with LLMs. Started with trying out #ChatGPT on the @TheUSMLE (https://t.co/RtRTwnzbCe) to where we are today. Still trying to restore the patient-physician relationship in encounters. Keynote by @EricTopol #IM2024 @ACPIMPhysicians #AI #ArtificialInteligence https://t.co/BcxHm9XNt8

1:50 PM · Apr 18, 2024

9
3

RT @TLeungMD: Where we're at with LLMs. Started with trying out #ChatGPT on the @TheUSMLE (https://t.co/RtRTwnzbCe) to where we are today.…

1:55 PM · Apr 18, 2024

9
3

RT @TLeungMD: Where we're at with LLMs. Started with trying out #ChatGPT on the @TheUSMLE (https://t.co/RtRTwnzbCe) to where we are today.…

8:35 PM · Apr 18, 2024

9
3

@sasuke___420 @yoimnotkesku @irl_danB @yacineMTB Citation? Unless your claim is simply that some stuff in Common Crawl might be related to those tests, and might randomly be in the training set. Here is my citation that ChatGPT-3.5 can do as well as a 3rd year medical student without fine-tuning or RAG. https://t.co/sM9olKU7vy

10:29 PM · May 24, 2024

0
0