ResearchTasksLLM Agent ReasoningLLM Agent ReasoningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedWebArenaARES46.5Accuracy7Mar 10, 2026BrowseComp-PlusRule-Based (High)42.7Accuracy7Mar 10, 2026