ResearchTasksTool-use Factuality EvaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedBFCL TaskGPT-OSS-120B76Factuality Score42May 4, 2026InvivoQueryQwen3-30B-A3B78Factuality Score42May 4, 2026Entity TaskQwen3-30B-A3B88Factuality Score42May 4, 2026