Larsen Cundric· @larsencc · X·· 7 小时前AI 评分34
AI 导读
希望看到更多公开的端到端智能体基准测试
正文
Would love to see more public e2e agentic benchmarks
Introducing AgentMail Evals. We tested how AI agents use tools: 25 model and harness combinations, seven email tasks, with AgentMail as the proxy.在 X 查看被引用的帖子
来源：Larsen Cundric · x.com