ResearchTasksZero-shot performance evaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedLM Eval Harness (HellaSwag, BoolQ, WinoGrande, PiQA, ARC-easy, ARC-challenge) zero-shotGIFT-SW75.46Mean Accuracy60Feb 26, 2026HellaSwag, BoolQ, WinoGrande, PiQA, ARC-easy, and ARC-challenge Zero-shot LM Eval HarnessFT77.02Mean Accuracy24Feb 26, 2026
LM Eval Harness (HellaSwag, BoolQ, WinoGrande, PiQA, ARC-easy, ARC-challenge) zero-shotGIFT-SW75.46Mean Accuracy60Feb 26, 2026
HellaSwag, BoolQ, WinoGrande, PiQA, ARC-easy, and ARC-challenge Zero-shot LM Eval HarnessFT77.02Mean Accuracy24Feb 26, 2026