ResearchTasksHuman Evaluation of Multilingual CapabilitiesHuman Evaluation of Multilingual CapabilitiesFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMultilingual human evaluationClaude-3-Opus4.15Score (Arabic)5Feb 26, 2026