Sourcegraph Blog
2026-06-16 00:00 UTC
By Stephanie Jarmak
USR-0064-20260616-ai-specialis-04bba4c5
Sourcegraph MCP server and a cheaper model beat a Mythos-class model alone
On nine CodeScaleBench tasks designed to evaluate agent effectiveness in large codebases, Claude Sonnet 4.6 with the Sourcegraph MCP server outscored Fable 5, winning six of nine at roughly half the cost for each point of quality.
On nine CodeScaleBench tasks designed to evaluate agent effectiveness in large codebases, Claude Sonnet 4.6 with the Sourcegraph MCP server outscored Fable 5, winning six of nine at roughly half the cost for each point of quality.
Full article content could not be extracted automatically. Read the original below.
Source:
Sourcegraph Blog
· localhost:5174