ResearchTasksMorphology ReasoningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedTime-MMD Traffic (test)KAIROSAGENT-4B (+ Turn-Level Reward RL)43.88Accuracy7May 29, 2026Time-MMD Energy (test)GPT-5.284.12Accuracy7May 29, 2026Time-MMD Climate (test)DeepSeek-R199.18Accuracy7May 29, 2026