ResearchTasksMathematical & Symbolic ReasoningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedOmni-MATH Tier 2Halo42.7Success Rate (SR)6Feb 26, 2026MATH Tier 1Halo38.5Success Rate (SR)6Feb 26, 2026GSM8K (Tier 1)Halo89.2SR6Feb 26, 2026