MCPMark Verified
Stabilized, version-pinned subset of MCPMark's standard tasks for reliable and reproducible MCP evaluation.
MCPMark Verified is the stabilized, version-pinned default standard task set for MCPMark, an evaluation suite/benchmark for agentic models in real MCP tool environments such as Notion, GitHub, Filesystem, Postgres, and Playwright. It is designed for more reliable and reproducible MCP evaluation with pinned environments and tightened verifiers across 127 standard tasks.

Recent stories
0 linked stories
No linked stories yet.