ResearchTasksReasoning trajectory meta-evaluationReasoning trajectory meta-evaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMeta-m&m'so3-mini88.56Efficiency10May 15, 2026Meta-GTAClaude-Sonnet-494.64Efficiency10May 15, 2026