ResearchDatasetsAB-OSFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsSTRINGAB-OS61.4LLM Judge Accuracy9Agentic Task SolvingAB-OS79.7Pass@39String ExtractionAB-OS61.4Exact Match9