ResearchTasksAgent Performance EvaluationAgent Performance EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedHarness-BenchFairyClaw74.6Combined Score12May 20, 2026MCP-BenchReAct46.8Task Fulfillment7May 12, 2026