ResearchTasksSpan-level machine translation error detectionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedWMT MQM (ZH-EN) 2023 (test)Haiku 4.550.25Precision6Mar 23, 2026WMT MQM EN-DE 2023 (test)MQM #239.02Precision6Mar 23, 2026MQM EN-ZH annotations 2024 (test)MQM #235.95Precision6Mar 23, 2026WMT MQM (EN-DE) 2022 (test)MQM #142.66Precision6Mar 23, 2026