ResearchTasksprompt_genprompt_genFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedConTest 200 with_hdsSentBERT0.77Spearman Rho12Jun 2, 2026McDiv full no_hds ~2KSentBERT0.796Spearman Rho6Jun 2, 2026McDiv nuggets ~1K, no_hdsSentBERT0.728Spearman Rho6Jun 2, 2026