ResearchTasksCommonsense Reasoning and Knowledge UnderstandingFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedCommonsense Reasoning and Knowledge Suite (ARC, HellaSwag, LAMBADA, PIQA, WinoGrande, MMLU)Qwen3-8B83.42ARC-e Accuracy13Apr 16, 2026
Commonsense Reasoning and Knowledge Suite (ARC, HellaSwag, LAMBADA, PIQA, WinoGrande, MMLU)Qwen3-8B83.42ARC-e Accuracy13Apr 16, 2026