Unverified50% confidenceFactExact time
Agent's Last Exam 是由 Scale AI 与学术界联合设计的 Agent 能力基准测试
1
Sources
50%
Confidence
Long-term
Relevance
7/13/2026
First Seen
Sources
GPT-5.6三档模型解析：Sol/Terra/Luna重写Agent成本结构
bilibiliTerminator-AI7/10/2026
Related Claims
UnverifiedAgent's Last Exam 是专为评估大模型自主代理能力设计的高难度基准，要求多步骤任务中持续调用外部工具、维持长上下文记忆并自我修正83% similarUnverifiedAgents' Last Exam is an evaluation system covering 55 professional domains that simulates long-running professional workflows.75% similarUnverifiedWhen selecting AI Agent building tools, one should verify whether there is a complete draft-test-publish workflow, out-of-the-box version management and one-click rollback, fine-grained permission controls, and multi-channel deployment with shared configuration.70% similarUnverified长周期Agent任务被业界公认为区分真正智能与表面流利模型的关键试金石70% similarUnverifiedTesting platforms such as Applitools, Testim, and mabl are also actively exploring the application of AI Agents in software testing.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/501724API
curl https://kongchang.com/api/v1/knowledge/claims/501724MCP
get_claim(id=501724)