ResearchDatasetsGSM8K, HumanEval, MMLU, AQuA, and MNLIFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsToken Usage AnalysisGSM8K, HumanEval, MMLU, AQuA, and MNLI Aggregate (official evaluation)—Primary metric0
Token Usage AnalysisGSM8K, HumanEval, MMLU, AQuA, and MNLI Aggregate (official evaluation)—Primary metric0