ResearchTasksHorizon GeneralizationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedFOL Uniform rewardGemma-2-9b-it227.48Max LR6Jun 1, 2026FOL Sine-trend rewardGemma-2-9b-it186.81Max LR Value3Jun 1, 2026FOL Gaussian rewardGemma-2-9b-it137.19Max LR3Jun 1, 2026