ResearchTasksMulti-task Language ReasoningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedReasoning and Language Understanding Suite (GSM8K, ARC-C, MEDQA, BOOLQ, COLA)Hard-Routed MoR-LoRA90.67GSM8K Accuracy6Jul 1, 2026
Reasoning and Language Understanding Suite (GSM8K, ARC-C, MEDQA, BOOLQ, COLA)Hard-Routed MoR-LoRA90.67GSM8K Accuracy6Jul 1, 2026