Inter-Model Variability of ChatGPT, Gemini and Claude in Treatment Recommendations for Unruptured Intracranial Aneurysms
Anish Narayan, Frederick Mariajoseph, Malik Farooq, Adrian Praeger, Ronil Chandra, Idrees Sher, Lee-Anne Slater, Calvin Gan, Andrew Gauden, Hamed Asadi, Justin Moore · 2026
Read Inter-Model Variability of ChatGPT, Gemini and Claude in Treatment Recommendations for Unruptured Intracranial Aneurysms by Anish Narayan, Frederick Mariajoseph, Malik Farooq, Adrian Praeger, Ronil Chandra, Idrees Sher, Lee-Anne Slater, Calvin Gan, Andrew Gauden, Hamed Asadi, Justin Moore (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13582248.txt.
Description
Anish Narayan and co-authors check whether top AI chatbots agree on brain aneurysm care. Their 2026 study fed sixty-seven real cases of unruptured aneurysms to ChatGPT, Gemini, and Claude, five runs each. It compared their treatment advice with a specialist team's consensus and a standard scoring tool.
Each model agreed with itself almost perfectly across runs. With each other, less so: ChatGPT and Gemini behaved near-identically, while Claude stood apart, usually on the cautious side. In one case in five the three split. Against the specialist team, ChatGPT and Gemini leaned toward treating; Claude leaned more conservative than the scoring tool. The authors warn clinicians to expect patients arriving with model-shaped expectations.
Catalog record
| CREATOR | Anish Narayan, Frederick Mariajoseph, Malik Farooq, Adrian Praeger, Ronil Chandra, Idrees Sher, Lee-Anne Slater, Calvin Gan, Andrew Gauden, Hamed Asadi, Justin Moore |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 47 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |