ResearchTasksAutonomous Agent Problem SolvingFor AI assistantsMarkdownContent indexAutonomous Agent Problem SolvingFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedHumanity's Last ExamChatGPT-Agent41.6Avg@319Apr 23, 2026