ResearchTasksZero-shot General EvaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedZero-shot Task Suite (HellaSwag, MathQA, MMLU, OpenBookQA, WinoGrande, GSM8K, HumanEval)FP1682.72HellaSwag Accuracy31Jun 2, 2026
Zero-shot Task Suite (HellaSwag, MathQA, MMLU, OpenBookQA, WinoGrande, GSM8K, HumanEval)FP1682.72HellaSwag Accuracy31Jun 2, 2026