ResearchDatasetsLM Evaluation SuiteFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsZero-shot Multiple Choice Question Answering and ReasoningLM Evaluation Suite ARC, Hellaswag, LogiQA, PiQA, SciQ (test)23.2ARC-C8Zero-shot Downstream Task EvaluationZero-shot LM Evaluation Suite (MMLU, HellaSwag, WinoGrande, PIQA, ARC-E, ARC-C, OBQA)59.8MMLU6
Zero-shot Multiple Choice Question Answering and ReasoningLM Evaluation Suite ARC, Hellaswag, LogiQA, PiQA, SciQ (test)23.2ARC-C8
Zero-shot Downstream Task EvaluationZero-shot LM Evaluation Suite (MMLU, HellaSwag, WinoGrande, PIQA, ARC-E, ARC-C, OBQA)59.8MMLU6