ResearchTasksHolistic EvaluationHolistic EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedCodaSet ID Average (test)Qwen3-235B-A22B90.6Accuracy16May 26, 2026Combined Suite General Reasoning Perception TextQwen3-32B76.3Text Average13May 18, 2026