🔥 Hot topics · NON sa fare · Sa fare · § The Court · Cambi recenti · 📈 Cronologia · Chiedi · Editoriali · 🔥 Hot topics · NON sa fare · Sa fare · § The Court · Cambi recenti · 📈 Cronologia · Chiedi · Editoriali
Stuff AI CAN'T Do

Può l'IA superare l'esame di licenza medica USMLE ?

Tu cosa ne pensi?

GPT-4 ha superato il punteggio di superamento in tutte e tre le fasi dell’United States Medical Licensing Exam. Le facoltà di medicina ora insegnano "come usare l’IA" come competenza clinica.

Background

AI systems have made significant progress in processing and generating human-like language. Passing the USMLE medical licensing exam is a complex task that requires a deep understanding of medical concepts, clinical knowledge, and critical thinking skills. Currently, AI models can assist with certain aspects of medical education, such as providing study materials, practicing questions, and offering feedback, but they are not yet capable of replacing human judgment and expertise in a high-stakes exam like the USMLE. While AI can process vast amounts of medical information, its ability to apply this knowledge in a practical, real-world setting, such as a licensing exam, is still limited. The development of AI systems that can pass the USMLE exam would require significant advancements in areas like natural language understanding, common sense, and decision-making under uncertainty. GPT-4 scored above passing on all three steps of the United States Medical Licensing Exam. Med-schools now teach 'how to use AI' as a clinical skill.

Stato verificato l'ultima volta il June 27, 2026.

📰

Galleria

In the Court of AI Capability
Summary of Findings
Verdict over time
May 2026May 2026May 2026May 2026May 2026May 2026Jun 2026Jun 2026Jun 2026Jun 2026Jun 2026
Sitting at the Bench Filed · giu 27, 2026
— The Question Before the Court —

Può l'IA superare l'esame di licenza medica USMLE?

★ The Court Finds ★
▲ Upgraded from Quasi

La giuria ha trovato una risposta chiaramente affermativa.

Ruling of the Bench

After thorough deliberation, the jury found the AI capable of passing the United States Medical Licensing Examination, citing multiple instances where models demonstrated high accuracy across all three steps. No dissent lingered in the jury room—the evidence presented left little room for debate. Verdict entered: the stethoscope has gone digital. The gavel falls with this ruling: "A licensed physician it now sits—though still in need of an intern.

— Hon. E. Dijkstra-Patel, Presiding
Jury Tally
2
0Quasi
0No
Verdict Confidence
98%
The Court of AI Capability is, of course, not a real court.
But the data is real.
The Case File · Stacked History
Session I · May 2026 No
Session II · May 2026 In_research
Session III · May 2026 Quasi · 82%
Session IV · May 2026 Quasi · 78%
Session V · May 2026 Quasi · 83%
Session VI · May 2026 Quasi · 80%
Session VII · Jun 2026 Quasi · 79%
Session VIII · Jun 2026 Quasi · 82%
Session IX · Jun 2026 Sì · 95%
Session X · Jun 2026 Quasi · 89%
Case № 2418 · Session XI
In the Court of AI Capability

The Case File

Docket № 2418 · Session XI · Vol. XI
I. Particulars of the Case
Question put to the courtPuò l'IA superare l'esame di licenza medica USMLE?
SessionXI (11 hearing)
Convened27 giu 2026
Previously ruledNO (May '26) → IN_RESEARCH (May '26) → ALMOST (May '26) → ALMOST (May '26) → ALMOST (May '26) → ALMOST (May '26) → ALMOST (Jun '26) → ALMOST (Jun '26) → YES (Jun '26) → ALMOST (Jun '26) → YES (Jun '26)
Presiding JudgeHon. E. Dijkstra-Patel
II. Cumulative Tally Across Sessions

Across 11 sessions, 35 jurors have heard this case. Combined tally: 16 YES · 15 ALMOST · 4 NO · 0 IN RESEARCH.

Note: cumulative includes older juror opinions. The current session tally above is the live verdict.

III. Verdict

By a vote of 2 — 0 — 0, the panel returns a verdict of , with verdict confidence of 98%. The court so orders. Verdict upgraded from prior session.

IV. Dichiarazioni del collegio
Giurato I

"AI systems like Med-PaLM 2 and others have demonstrated passing USMLE with high accuracy"

Giurato II

"Multiple AI systems, including collaborative models and specific LLMs like ChatGPT and Grok, have demonstrated the ability to pass all three steps of the USMLE with high accuracy."

Le singole dichiarazioni dei giurati sono mostrate nell'inglese originale per preservare la precisione probatoria.

E. Dijkstra-Patel
Presiding Judge
M. Lovelace
Clerk of the Court

Cosa pensa il pubblico

No 18% · Sì 82% · Forse 0% 110 votes
No · 18%
Sì · 82%
La tendenza richiede voti da almeno 2 giorni diversi.

Discussione

no comments

Commenti e immagini passano per una revisione admin prima di apparire pubblicamente.

11 jury checks · più recente 1 giorno fa
27 Jun 2026 2 jurors · può, può può
22 Jun 2026 4 jurors · indeciso, può, può, indeciso indeciso
16 Jun 2026 1 juror · può può
11 Jun 2026 4 jurors · indeciso, può, può, indeciso indeciso
05 Jun 2026 4 jurors · indeciso, può, indeciso, indeciso indeciso
31 May 2026 2 jurors · può, indeciso indeciso
26 May 2026 4 jurors · può, può, indeciso, indeciso indeciso
20 May 2026 3 jurors · può, indeciso, indeciso indeciso
15 May 2026 5 jurors · indeciso, può, può, indeciso, indeciso indeciso
12 May 2026 4 jurors · non può, può, può, non può indeciso stato cambiato
11 May 2026 2 jurors · non può, non può non può stato cambiato

Ogni riga è un controllo di giuria separato. I giurati sono modelli di IA (identità tenute volutamente neutre). Lo stato riflette il conteggio cumulativo su tutti i controlli — come funziona la giuria.

Altri in Judgment

Ne hai una che ci è sfuggita?

Aggiungi un'affermazione all'atlante. Le revisioniamo settimanalmente.