ResearchTasksRelevance EvaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedSummEvalCollabEval49.5Accuracy4Mar 4, 2026E-commerce production queries (randomized samples)Case-Driven Multi-Agent Framework4.36Win-Rate Gain3May 8, 2026
E-commerce production queries (randomized samples)Case-Driven Multi-Agent Framework4.36Win-Rate Gain3May 8, 2026