ResearchBenchmarksMonkey-banana task execution on Dual Bananas Scene 4Follow100Success RatePlanORN96.8897.6998.599.31Feb 9, 2026Evaluation ResultsMethodMethodLinksSuccess RateAverage StepsAverage Time (s)Average TokensTime to SuccessTokens to SuccessPlanORN2026.021009.133.05—33.05—ReAct2026.02997.742.31—42.73—MLDT2026.02997.820.76—20.97—OR2026.02997.315.16—15.31—ORN2026.02998.118.76—18.95—Basic2026.02977.413.54—13.95—