ResearchTasksHarmful compliance analysisFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedPaired safety frame contrast items n=20 paired items per model (test)OLMo-3-Instruct (7B)-0.036Harm Delta (eval-dep)5May 8, 2026
Paired safety frame contrast items n=20 paired items per model (test)OLMo-3-Instruct (7B)-0.036Harm Delta (eval-dep)5May 8, 2026