ResearchDatasetsAgent Task BenchmarkFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsAgentic Task PerformanceAgent Task Benchmark 240 documents 1.0 (Evaluation set)92.3Information Lookup Success Rate4
Agentic Task PerformanceAgent Task Benchmark 240 documents 1.0 (Evaluation set)92.3Information Lookup Success Rate4