ResearchTasksAggregate Out-of-Domain EvaluationFor AI assistantsMarkdownContent indexAggregate Out-of-Domain EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedAverage GPQA, LSAT, MMLU-1000Agentica-24k0.38Pass@111Feb 26, 2026