ResearchTasksSibling-model judgmentFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedMMLU-ProGnosis-SelfJudge0.83AUROC8Feb 26, 2026TriviaQAGnosis-SelfJudge0.89AUROC8Feb 26, 2026Math AMC12 + AIME24 25 + HMMTFeb2025Gnosis-SelfJudge0.97AUROC8Feb 26, 2026