ResearchTasksMeeting claim evaluationMeeting claim evaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedprivate_data (test)gpt-5.474.5Accuracy2Apr 24, 2026city_council (test)gpt-5.476Accuracy2Apr 24, 2026city_council & private_data overall (test)gpt-5.475.4Accuracy2Apr 24, 2026