ResearchTasksDialogue ReasoningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedMUTUALLED80.8Accuracy38May 15, 2026DIPLOMATAutoMix + T168.2AIBC Score12Feb 26, 2026IndiRefAgentic-Image50Temporal Accuracy4Apr 24, 2026MuTual (dev)FOCAL REASONER73.4R4@13Feb 26, 2026