ResearchTasksSoftware Engineering ReasoningSoftware Engineering ReasoningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedCLAW-EvalTACT-GATE61.5Pass@316May 8, 2026Terminal-Bench (TB2) 2.0TACT-GATE36Resolution Rate16May 8, 2026