ResearchTasksMulti-hop Multiple-choice Question AnsweringMulti-hop Multiple-choice Question AnsweringFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedT2S-Bench-MR 1.0 (test)Gemini-2.5-Pro81.4Overall EM45Mar 5, 2026