ResearchDatasetsLLM Foundational CapabilitiesLLM Foundational CapabilitiesFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsZero-shot Reasoning and Language ModelingLLM Foundational Capabilities (SciQ, PIQA, Winogrande, ARC, HellaSwag, LogiQA, BoolQ, LAMBADA) zero-shot94.1SciQ Accuracy17
Zero-shot Reasoning and Language ModelingLLM Foundational Capabilities (SciQ, PIQA, Winogrande, ARC, HellaSwag, LogiQA, BoolQ, LAMBADA) zero-shot94.1SciQ Accuracy17