ResearchTasksZero-shot Evaluation AggregateFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedARC-C, BoolQ, HellaSwag, MMLU, OBQA, PIQA, RTE, Winogrande AggregateUNPRUNED61.6Average Accuracy13Apr 21, 2026
ARC-C, BoolQ, HellaSwag, MMLU, OBQA, PIQA, RTE, Winogrande AggregateUNPRUNED61.6Average Accuracy13Apr 21, 2026