ResearchTasksEnterprise interface interactionEnterprise interface interactionFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedWorkArena L2 full benchmarkGPT-569.4Success Rate3Apr 10, 2026WorkArena L2 (test)A3-Qwen3.5-9B9.7Success Rate2Apr 10, 2026