ResearchBenchmarksVision-Language Navigation on Suburban simulation sceneFollow50Success Rate (SR)TARIC12.87222.51132.1541.789May 29, 2026Evaluation ResultsMethodMethodLinksSuccess Rate (SR)SPLConfidence Failure Rate (Fail@CF)CFSR @ 10mCFSR @ 25mCFSR @ 50mTARIC2026.05504027927564EzReal2026.05333450.3654335.7GPT-4o-GeNie2026.0527.33558603028StreamVLN2026.0524.72564482219.3NaviLLM2026.0522.3247150.32020.3NoMaD2026.0514.318784712.38