npmjs.org : coding-agent-benchmarks
Testing coding agents (GitHub Copilot CLI, Claude Code, etc.) with your repo's context to evaluate their code generation quality.
Registry
-
Source
- Homepage
- JSON
- codemeta.json
purl: pkg:npm/coding-agent-benchmarks
Keywords:
coding-agent
, benchmark
, evaluation
, copilot
, github-copilot
, claude
, claude-code
, ai
, llm
, openai
, gpt
, testing
, code-quality
, code-generation
, code-standards
, lint
, eslint
, ci-cd
, automation
, developer-tools
, prompt-testing
, ai-testing
License: MIT
Latest release: 3 days ago
First release: 8 days ago
Last synced: about 20 hours ago