ResearchTasksWeb Agent InteractionWeb Agent InteractionFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedWebShopENVRL-GiGPO88.4Score14Jun 17, 2026RUC suite (test)w/ DUDE60Success Rate (News)9May 12, 2026WorkArena L1Coverage0.803Cumulative Runtime (h/m)3May 29, 2026