ResearchTasksAggregated LLM EvaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast Updated8 Standard Benchmarks AggregateFull model73.7Average Accuracy5May 4, 2026Balanced Objective Aggregate SuiteCAMEL53.2Weighted Average Score5Mar 10, 2026