ResearchDatasetsAlpaca-LlamaAlpaca-LlamaFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsModel UtilityAlpaca-Llama 3 Utility Benchmarks47.36ARC-c Score7Safety AlignmentAlpaca-Llama Safety Sets 397I-Mali7