Fig. 2: Performance of open-source LLMs in Eurorad dataset (n = 1933) and local brain MRI dataset (n = 60).
From: Benchmarking the diagnostic performance of open source LLMs in 1933 Eurorad case reports
Error bars indicate adjusted 95% confidence intervals. Reader 1 and 2 were radiologists with two and four years of dedicated neuroradiology experience each.
