ResearchTasksOnline auditingOnline auditingFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedAFTRAJ-2KAgentForesight-7B77.36Exact-F1 (Math)15May 12, 2026Who&WhenAgentForesight-7B57.69Step Accuracy8May 12, 2026