ResearchDatasetsshared human-rated question setshared human-rated question setFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsLLM-judge evaluation on humanities rubricshared human-rated question set n=100 (test)4.88Answer Accuracy16
LLM-judge evaluation on humanities rubricshared human-rated question set n=100 (test)4.88Answer Accuracy16