microsoft/CodeXGLUE resource

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1839 stars · 392 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

CodeXGLUE is a benchmark dataset and open challenge from Microsoft for code intelligence, covering tasks like code search, code completion, and code-to-code translation. It includes a collection of datasets and a platform for evaluating and comparing pre-trained code models such as CodeBERT.

Use cases

• benchmarking pre-trained models on code understanding tasks
• evaluating code completion models
• comparing code-to-code translation systems
• training models for natural language code search
• researching clone detection and defect detection
• building code summarization models

When to choose

• you need standardized datasets for code intelligence research
• you want to compare your model against published baselines on code tasks
• you are studying pre-trained models for programming languages

When to avoid

• you need a production code intelligence tool rather than a benchmark
• your task is outside the covered code intelligence tasks
• you need actively maintained datasets with recent updates

Facets

dataset · maturity maintenance

machine-learning nlp search-engine benchmarking machine-learning developer-tools programming-languages python cross-platform code-intelligence benchmark codebert code-search code-completion code-translation program-synthesis microsoft-research natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="microsoft/CodeXGLUE")