ResearchTasksChinese ReasoningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedOCNLIQwen3.5-9B74.4Accuracy9May 4, 2026CLUEWSCQwen3-14B92.73Accuracy9May 4, 2026C3Llama-3.3-70B-Instruct96.88Accuracy8May 4, 2026