← 返回专题广场
eval-sys
1 个项目 · ⭐ 4591
MCPMark is a comprehensive, stress-testing MCP benchmark designed to evaluate model and agent capabilities in real-world MCP use.
Python
⭐ 459
⑂ 44
Apache-2.0
· 2026-06-12推送
2026-06-12
最近推送