ResearchTasksWorld Knowledge and Reading ComprehensionFor AI assistantsMarkdownContent indexWorld Knowledge and Reading ComprehensionFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedLM Evaluation Harness NQ, MMLU STEM, ARC, SciQ, LogiQA, BoolQMistral-7B Base29.81NQ Accuracy15Feb 26, 2026
LM Evaluation Harness NQ, MMLU STEM, ARC, SciQ, LogiQA, BoolQMistral-7B Base29.81NQ Accuracy15Feb 26, 2026