ResearchTasksReasoning RobustnessReasoning RobustnessFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMathematical Reasoning Perturbation ExperimentsR1-Qwen-7B (Base)76.2Robustness Perturbation Success Rate (R-PSR)4Mar 4, 2026
Mathematical Reasoning Perturbation ExperimentsR1-Qwen-7B (Base)76.2Robustness Perturbation Success Rate (R-PSR)4Mar 4, 2026