ResearchDatasetsDBDBFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsCode Correctness EvaluationDB68.6F1 Score24Database Querying Agent TaskDB70.1Success Rate19InstanceOf triple classificationDB99K-242 (test)94.21Accuracy13Private Information RetrievalDB 4GB (test)2,201QPS9Private Information RetrievalDB 1GB (test)8,244QPS9Link predictionDB100k0.419MRR9Private Information RetrievalDB 2GB (test)723.5Throughput (QPS)4Topic ClassificationDB98.5Accuracy4