ResearchDatasetsARC, MMLU, GPQAFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsOut-of-Distribution ReasoningARC-c, MMLU-Pro, GPQA-diamond OOD Evaluation Suite38.4ARC-c Accuracy (Avg@32)6
Out-of-Distribution ReasoningARC-c, MMLU-Pro, GPQA-diamond OOD Evaluation Suite38.4ARC-c Accuracy (Avg@32)6