ResearchTasksReasoning EfficiencyReasoning EfficiencyFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedConstraint Reasoning (CR)SEM-CTRL123.3Ntokens4Mar 4, 2026Syllogism Generation Task (SGS)SEM-CTRL250.2Ntokens4Mar 4, 2026ScienceWorld (Seen)BPO83.16Success Rate (%)3May 19, 2026