ResearchDatasetsGSM8K, HumanEval, MMLU, AQuA, and MNLIGSM8K, HumanEval, MMLU, AQuA, and MNLIFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA 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