Large Language Model Cost and Performance: A Comprehensive Analysis in the Context of the Japan Radiology Board Examination
Closed-source, high-end LLMs exhibit superior performance in JRBE, and translating questions into English by themselves further enhances their accuracy. There is a significant positive correlation between the cost of LLMs and their performance, whereas the release date does not significantly influence their performance.
Authors
- Masafumi Kidoh (ORCID: https://orcid.org/0000-0002-9589-7054)
- Toshinori Hirai (ORCID: https://orcid.org/0000-0003-1480-2197)
- Yoshinori Funama (ORCID: https://orcid.org/0000-0003-1797-9625)
- Hiroyuki Uetani (ORCID: https://orcid.org/0000-0002-0547-1210)
- Takeshi Nakaura (ORCID: https://orcid.org/0000-0002-9010-0341)
- Kaori Shiraishi
- Naofumi Yoshida (ORCID: https://orcid.org/0000-0003-3949-0089)
- Yasunori Nagayama (ORCID: https://orcid.org/0000-0003-3280-7346)
- Naoki Kobayashi (ORCID: https://orcid.org/0000-0002-0537-0604)
- Seitaro Oda (ORCID: https://orcid.org/0000-0002-0609-2191)
Institutions
- Kumamoto University (JP)
Publication Details
- Journal
- Journal of Computer Assisted Tomography
- Published
- 2025-11-03
- DOI
- https://doi.org/10.1097/rct.0000000000001807
- Primary Topic
- Radiology practices and education
- Type
- article
- Field-Weighted Citation Impact
- 0.00