ResearchTasksLong-context Temporal ReasoningLong-context Temporal ReasoningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedEventQAQwen3-4B RL finetuned on HanabiRewards0.856Accuracy (64K)2Feb 26, 2026