ResearchTasksPairwise Solution Preference PredictionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedData-centric Solution Preference Dataset (test)DeepSeek-V3.2 (Thinking mode)61.5Average Accuracy4Feb 26, 2026
Data-centric Solution Preference Dataset (test)DeepSeek-V3.2 (Thinking mode)61.5Average Accuracy4Feb 26, 2026