ResearchTasksValue ModelingFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedDAPO-Math-17k Qwen2.5-7B-Instruct policy (Held-out)V00.693Intra AUC2Feb 26, 2026DAPO-Math-17k Qwen3-4B-Instruct-2507 policy (Held-out)V00.689Intra AUC2Feb 26, 2026DAPO-Math-17k DeepSeek-R1-Distill-Qwen-1.5B policy (Held-out)V071Intra AUC2Feb 26, 2026