ResearchTasksAnswer correctness predictionAnswer correctness predictionFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedTriviaQA, HotpotQA, and MedMCQA In-Distribution Average (val)HEAD ENTROPY0.91Head Entropy12Feb 26, 2026TriviaQA, HotpotQA, and MedMCQA OOD Generalization Average (val)HEAD ENTROPY0.68Head Entropy6Feb 26, 2026TriviaQA (val)HEAD ENTROPY0.79Head Entropy1Feb 26, 2026MedMCQA (val)HEAD ENTROPY0.79Head Entropy1Feb 26, 2026HotpotQA (val)HEAD ENTROPY0.6Head Entropy1Feb 26, 2026
TriviaQA, HotpotQA, and MedMCQA In-Distribution Average (val)HEAD ENTROPY0.91Head Entropy12Feb 26, 2026
TriviaQA, HotpotQA, and MedMCQA OOD Generalization Average (val)HEAD ENTROPY0.68Head Entropy6Feb 26, 2026