ResearchTasksBest-of-N RerankingBest-of-N RerankingFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedAverage of 7 benchmarks (including AIME24, LeetCode) (test)DeepSeek-R1-Distill-Qwen-32B52Average Accuracy42May 20, 2026
Average of 7 benchmarks (including AIME24, LeetCode) (test)DeepSeek-R1-Distill-Qwen-32B52Average Accuracy42May 20, 2026