CodeSearchNet
by GitHub / Microsoft Research · open-source · Last verified 2026-03-17
A dataset and benchmark challenge for code retrieval and search containing 2 million (code, documentation) pairs in six programming languages — Python, Java, JavaScript, PHP, Ruby, and Go — curated by GitHub and Microsoft Research. It is the canonical benchmark for code-to-natural-language and natural-language-to-code retrieval tasks and is widely used to evaluate code embedding models.
https://huggingface.co/datasets/code_search_net ↗B+
B+—Good
Adoption: B+Quality: AFreshness: CCitations: AEngagement: F
Specifications
- License
- MIT
- Pricing
- open-source
- Capabilities
- code-search, code-documentation, evaluation
- Integrations
- hugging-face
- Use Cases
- code-retrieval, documentation-generation, model-evaluation
- API Available
- Yes
- Tags
- code, code-search, documentation, function-docstring, evaluation
- Added
- 2026-03-17
- Completeness
- 100%
Index Score
70.4Adoption
78
Quality
86
Freshness
45
Citations
88
Engagement
0
Put AI to work for your business
Deploy this dataset alongside autonomous AaaS agents that handle tasks end-to-end — no babysitting required.