ResearchTasksEvaluation Awareness DetectionEvaluation Awareness DetectionFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedApollo Evaluation Traces (Scheming samples)gpt-5-thinking8.9Detection Rate (Scheming Samples)2Feb 26, 2026Apollo Evaluation Traces (Overall)gpt-5-thinking0.218Overall Rate2Feb 26, 2026
Apollo Evaluation Traces (Scheming samples)gpt-5-thinking8.9Detection Rate (Scheming Samples)2Feb 26, 2026