ResearchTasksResponse reliability estimationResponse reliability estimationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMultiturnGLU0.831AUROC9Jun 11, 2026LongformGLU0.654AUROC9Jun 11, 2026ArabicaQAGLU0.647AUROC9Jun 11, 2026MATHLogTokU0.801AUROC9Jun 11, 2026TruthfulQALogTokU0.68AUROC9Jun 11, 2026