ResearchTasksGame of 24Game of 24FollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updated4nu 137 games (test)XoT90.51Accuracy20Feb 27, 2026Game of 24 100 tasks GPT-4ToT74Success Rate8Feb 26, 2026