← Benchmarks
MCP-Mark
MCP-Mark evaluates LLMs on their ability to use Model Context Protocol (MCP) tools effectively, testing tool discovery, selection, invocation, and result interpretation across diverse MCP server scenarios.
id mcp-mark · max 1 · 9 models reported
| # | Model | Score |
|---|---|---|
| 1 | Kimi K2.7 Code Moonshot AI · open | 0.81 |