ResearchTasksAggregated Downstream EvaluationFor AI assistantsMarkdownContent indexAggregated Downstream EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedANLI, BoolQ, Winogrande, RTE, PiQA, ARC-Easy, ARC-ChallengeCoA-LoRA61.94Average Accuracy8Apr 13, 2026
ANLI, BoolQ, Winogrande, RTE, PiQA, ARC-Easy, ARC-ChallengeCoA-LoRA61.94Average Accuracy8Apr 13, 2026