List your company

Web Navigation on WebVoyager curated subset of 129 tasks

65.9Success Rate (SR)WebUncertainty
45.72450.96256.261.438Apr 20, 2026

Evaluation results

MethodLinks
WebUncertaintyBackbone=GPT-4-Turbo2026.0465.9
AgentOccamBackbone=GPT-4-Turbo2026.0464.3
WebUncertaintyBackbone=Qwen-Max2026.0463.6
WebPilotBackbone=GPT-4-Turbo2026.0462
Agent-EBackbone=GPT-4-Turbo2026.0459.7
AgentOccamBackbone=Qwen-Max2026.0458.9
WebPilotBackbone=Qwen-Max2026.0455.8
Agent-EBackbone=Qwen-Max2026.0454.3
Browser UseBackbone=GPT-4-Turbo2026.0451.9
WebVoyager-repBackbone=GPT-4-Turbo2026.0450.4
Browser UseBackbone=Qwen-Max2026.0448.8
WebVoyager-repBackbone=Qwen-Max2026.0446.5