ResearchTasksAgentic EvaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedSimpleQAEFFGEN84Accuracy50Feb 26, 2026GAIAEFFGEN28.12Accuracy50Feb 26, 2026ClawEval 0424Claude Opus-4.670.4Pass^3 Score7Jun 16, 2026PinchBenchRing-2.6-1T87.6Avg@36Jun 16, 2026