ResearchTasksBias-Penalized Accuracy EvaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedLow-Resource Languages (LRLs)SFT76.96BPA9Feb 26, 2026High-Resource Languages (HRLs)SFT93.39Bias-Penalized Accuracy (BPA)9Feb 26, 2026EnglishSFT98.78Bias-Penalized Accuracy (BPA)9Feb 26, 2026