ResearchTasksGeneral Language IntelligenceFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedMMLU, GSM8K, BBH, TriviaQA, NQ latest available (test)GAC (Qwen2-72B + Llama-3)83.54MMLU26Feb 26, 2026Aggregate MIF, MMMLU, GPQA, ARC-C, BBH, MATH, GSM8K (all)Baseline58.24Mean Accuracy5Apr 30, 2026
MMLU, GSM8K, BBH, TriviaQA, NQ latest available (test)GAC (Qwen2-72B + Llama-3)83.54MMLU26Feb 26, 2026