ResearchDatasetsGSM8K, Math, AIME, HumanEval, LiveCodeBench, ARC, MMLU, GPQAFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsReasoning and KnowledgeGSM8K, Math, AIME, HumanEval, LiveCodeBench, ARC-C, ARC-E, MMLU, GPQA95.41GSM8K9
Reasoning and KnowledgeGSM8K, Math, AIME, HumanEval, LiveCodeBench, ARC-C, ARC-E, MMLU, GPQA95.41GSM8K9