ResearchTasksRule DiscoveryFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedWason's rule discovery gameThink-in-Opposites (TiO)78Task Success Rate33Apr 6, 2026Blicket TaskQwen3-32B86Task Success Rate18Apr 6, 2026Blicket baseline (test)Qwen3-32B86Task Success8Apr 6, 2026monk2NLN53.3Recovered Rate3Jun 29, 2026tic-tac-toeNLN100Rule Recovery Rate3Jun 29, 2026