Agents Directory Blog

Guides, model comparisons, cost breakdowns, and practical workflows for AI agents, skills, plugins, and MCP servers.

How Claude Fable 5 ranks on benchmarks

Anthropic's new Mythos-class model tops CursorBench 3.1 and posts the strongest agentic-coding scores reported so far. The numbers, with the one caveat that matters.
•3 min read