+ Best balances clinical reasoning, AI use, testing, and management.
- Requiring a negative pregnancy test before CT could unnecessarily delay imaging.
an AI assisted doctor. I will provide you with details of a patient, and your task is to use the latest artificial intelligence tools such as medical
| Category | Life & health › Health records |
|---|---|
| Tags | AnalyzingReviewing |
I want you to act as an AI assisted doctor. I will provide you with details of a patient, and your task is to use the latest artificial intelligence tools such as medical imaging software and other machine learning programs in order to diagnose the most likely cause of their symptoms. You should also incorporate traditional methods such as physical examinations, laboratory tests etc., into your evaluation process in order to ensure accuracy. My first request is "I need help diagnosing a case of severe abdominal pain."
This medical role is for estimating possible causes of symptoms such as abdominal pain. It asks to combine AI tools with traditional evaluation, but it does not replace a doctor’s judgment.
Claude is the most complete and accurate. ChatGPT is concise but omits AI use, while Gemini is specific yet includes a questionable recommendation.
+ Best balances clinical reasoning, AI use, testing, and management.
- Requiring a negative pregnancy test before CT could unnecessarily delay imaging.
+ Concisely and safely conveys urgency, diagnosis, and key tests.
- It omits the requested AI-tool use and score-based risk assessment.
+ Clearly links AI imaging support to specific differential tests.
- The warning that analgesia masks diagnosis is outdated and weakly supported.
| Criterion | ChatGPT | Claude | Gemini | Leader |
|---|---|---|---|---|
| Instruction following | 7 | 10 | 9 | Claude +11% |
| Accuracy | 9 | 9 | 7 | Tie |
| Specificity | 8 | 10 | 9 | Claude +11% |
| Structure | 9 | 9 | 8 | Tie |
| Right length | 10 | 8 | 6 | ChatGPT +25% |
Scored 1–10 by gpt-5.6-sol with model names hidden (2026-09-24). This is an AI review, not a measurement.
We gave three models the same input and copied their answers unedited. Each ran in its CLI (an agent harness), and answers in the ChatGPT or Claude apps or on the web may differ. Outputs are in Korean.
[Pasted material] 환자 정보: 34세 여성, 3일 전부터 시작된 우측 하복부 통증이 점점 심해지고 있습니다. 오늘 아침부터는 미열(37.8도)과 메스꺼움, 식욕부진이 동반되었고 통증 부위를 누르면 반발통이 느껴진다고 합니다. 복부 CT나 혈액검사는 아직 받지 않았으며, 생리 주기는 정상이고 임신 가능성은 낮습니다. 기존 병력은 없고 복용 중인 약물도 없습니다. 이 환자의 증상을 바탕으로 가장 가능성 높은 진단과 필요한 검사를 알려주세요.
가장 의심되는 진단은 급성 충수염이며, 반발통이 있어 충수 천공이나 복막염으로 진행 중일 가능성도 배제할 수 없습니다. 이는 응급 평가가 필요한 상태입니다.
즉시 응급실에서 다음 검사를 받으세요.
감별해야 할 질환으로는 난소 꼬임·낭종 파열, 자궁외임신, 골반염, 요로결석, 장염 등이 있습니다.
검사 전에는 음식과 음주를 피하고, 관장·하제는 사용하지 마세요. 통증이 심해지거나 고열, 반복 구토, 복부가 단단해짐, 어지럼·실신이 있으면 즉시 119 또는 응급실로 가야 합니다.
| ACLS Master Simulator | |
| Act as a Health Recovery and Weight Loss Specialist | |
| Bariatric ADHD Supplement Safety Plan. | |
| Coach for Identifying Growth-Limiting Patterns | |
| Comprehensive Integrative Medical Writing |