List your company

Web Navigation and Task Completion on Mind2Web Online

55.6SR (%) AvgMACU
52.06452.98253.954.818Jun 1, 2026

Evaluation results

MethodLinks
MACUSetup=Multi-Agent, Manager=Opus 3.5, Subagent backbone=Qwen2.5-72B2026.0655.63.433.615.1
MACUSetup=Multi-Agent, Manager=Qwen2.5-72B, Subagent backbone=Qwen2.5-72B2026.0652.40.223.65.1
Single-AgentSetup=Single-Agent, Manager=—, Subagent backbone=Qwen2.5-72B2026.0652.2—18.5—