MCP Atlas
MCP Atlas 是一个用于评估大型语言模型在 Model Context Protocol（MCP）相关任务上能力的基准测试。它通过设计一系列标准化测试场景，衡量模型对 MCP 协议的理解、工具调用及上下文管理等核心能力，为不同模型在 MCP 生态中的性能对比提供客观、可重复的评估框架。
Timeline (last 90 days)
On the MCP Atlas benchmark, Glimmer scored 75.5, Gemma 4 scored 54.2, and Qwen 3.6 scored 62.5.
Muse Glimmer scores 75.5 on the MCP Atlas tool-calling benchmark, leading Qwen 3.6; scores 74.6 on agentic search tasks; and scores 94.7 on the AIME mathematical reasoning benchmark.
All Facts (3)
MCP Atlas基于Anthropic提出的Model Context Protocol设计，测量模型在标准化工具调用协议下的Agent执行能力
85%UnverifiedMuse Glimmer scores 75.5 on the MCP Atlas tool-calling benchmark, leading Qwen 3.6; scores 74.6 on agentic search tasks; and scores 94.7 on the AIME mathematical reasoning benchmark.
60%UnverifiedOn the MCP Atlas benchmark, Glimmer scored 75.5, Gemma 4 scored 54.2, and Qwen 3.6 scored 62.5.
50%