Unverified80% confidenceFactTime unknown

Manus在GAIA基准测试Level 2上得分70.0%

1

Sources

80%

Confidence

Medium-term (~90 days)

Relevance

6/1/2026

First Seen

Valid until: 8/30/2026

Sources

Manus实测：三大真实场景验证通用AI Agent到底行不行

bilibili宇迪谈AI

Related Entities

Manusproduct GAIAconcept

Related Claims

UnverifiedManus在GAIA基准测试Level 3上得分57.7%79% similar UnverifiedManus在GAIA基准测试中取得了领先成绩76% similar UnverifiedManus在GAIA基准测试Level 1上得分86.5%，远超OpenAI Deep Research76% similar UnverifiedManus完成任务的速度最快，但报告质量在三者中排名最末55% similar Unverified通义千问3.6在SWE-Bench测试中得分78.8分，对比Claude Opus的80.9分54% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/20908

API

curl https://kongchang.com/api/v1/knowledge/claims/20908

MCP

get_claim(id=20908)