Unverified80% confidenceBenchmarkExact time

Stanford University's WebArena benchmark, released in 2023, showed that even the most advanced AI models achieve only about a 14% success rate on complex operational tasks on real web pages

1

Sources

80%

Confidence

Long-term

Relevance

7/18/2026

First Seen

Sources

Giving AI Root Access to a Computer and a Bank Card: A Full Breakdown of the Autonomous Money-Making Experiment

Related Entities

WebArenaconcept Stanford Universitycompany

Related Claims

UnverifiedAI智能体操作网页的核心技术难题是actuation（执行操作），源于AI模型的感知-行动鸿沟69% similar UnverifiedAI Agent在执行网页任务时面临的核心挑战来自Web的异构性69% similar Unverified斯坦福大学2024年AI指数报告显示，编程类任务是AI渗透速度最快的工作领域之一68% similar UnverifiedAI代理在面对动态加载页面、验证码、多因素认证等情况时仍存在较高的失败率66% similar UnverifiedAI的核心优势在于处理复杂高难度任务而非当作搜索引擎使用66% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/680680

API

curl https://kongchang.com/api/v1/knowledge/claims/680680

MCP

get_claim(id=680680)