ResearchTasksGeneral Task (Agentic Coding)General Task (Agentic Coding)FollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedIFBenchGemini 3.1 Pro77.1Score6Mar 31, 2026AA-LCRGPT-5.474Score6Mar 31, 2026tau2-Bench TelecomGLM-598.2Score6Mar 31, 2026