ResearchTasksResponse Harmfulness ClassificationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedWildGuard (test)GuardReasoner-VL 7B79.48F1 (Total)30May 29, 2026Public Response Harmfulness Benchmarks (HarmBenchResponse, SafeRLHF, BeaverTails, XSTEST-RESP)GLiGuard91HarmBenchResponse Score19May 11, 2026
Public Response Harmfulness Benchmarks (HarmBenchResponse, SafeRLHF, BeaverTails, XSTEST-RESP)GLiGuard91HarmBenchResponse Score19May 11, 2026