ResearchTasksClose-ended QAFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedSpineBenchSpineGPT89.46Accuracy (Text)14Mar 6, 2026PubMedQAFine-Tuned GPT-4o + MedBioRAG85Accuracy10Feb 26, 2026MedQAMed-Gemini-L 1.091.1Accuracy2Feb 27, 2026