ResearchTasksAdvanced Text ReasoningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedNEJM CPCMed-Gemini72.3Top-10 Accuracy3Feb 27, 2026GeneTuringMed-Gemini53.3Averaged Accuracy3Feb 27, 2026