ResearchTasksLong-horizon web tasksFor AI assistantsMarkdownContent indexLong-horizon web tasksFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedWebTailBench long-horizon tasksQwen-3-VL-32B40.2SR@5034May 13, 2026