ResearchTasksZero-shot Evaluation AggregateZero-shot Evaluation AggregateFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA 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