ResearchTasksQuality-judgment accuracyFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedLLMBar ZH conditionDeepSeek86.5Strict Accuracy (%)4Jun 15, 2026LLMBar EN conditionDeepSeek89.5Strict Accuracy (LLMBar EN)4Jun 15, 2026LLMBar LSDeepSeek86.5Strict Accuracy4Jun 15, 2026