ResearchBenchmarksMonkey-banana task execution on Dual Bananas Scene 6Follow100Success RateReAct89.692.39597.7Feb 9, 2026Evaluation ResultsMethodMethodLinksSuccess RateAverage StepsAverage Time (s)Average TokensTime to Success (s)Tokens to SuccessReAct2026.0210012.479.82—79.82—ORN2026.0210011.632.81—32.81—OR2026.029911.326.7—26.97—PlanORN2026.029919.678.67—79.47—Basic2026.029011.220.1—22.34—MLDT2026.029010.628.91—32.12—