ResearchTasksPairwise Solution Preference PredictionPairwise Solution Preference PredictionFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA 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