CodeXGLUE

Microsoft CodeXGLUE is a 10-task, 14-dataset suite for code understanding and generation; EleutherAI lm-eval currently ships only the code-to-text group.

Also known as: Code-X-GLUE, Code X GLUE, codexglue, code2text

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categorycoding
SubcategoryMicrosoft 10-task code understanding and generation suite; lm-eval ships code-to-text
Page statusactive
Metricsmoothed BLEU-4 (lm-eval code2text); suite-wide metrics vary by task
Directionhigher_is_better
Dataset licenceMIT (repository code); C-UDA (datasets, per README)
PublisherMicrosoft Research Asia, Developer Division, and Bing

What it measures

CodeXGLUE (General Language Understanding Evaluation for CODE) is Microsoft's 2021 suite of 10 code-intelligence tasks on 14 datasets. The four scenarios are code-code (clone detection, defect detection, cloze, completion, repair, translation), text-code (search and text-to-code), code-text (summarization), and text-text (documentation translation). EleutherAI lm-evaluation-harness implements only the code-to-text group under lm_eval/tasks/code_x_glue: generate a natural-language docstring from tokenized code in Go, Java, JavaScript, PHP, Python, or Ruby. That wrap is CodeSearchNet-derived summarization scored with smoothed BLEU-4, not the whole suite.

Task format

lm-eval code2text: generate_until on Hub datasets CM/codexglue_code2text_*. doc_to_text joins code_tokens; doc_to_target joins docstring_tokens. Beam 10, max_gen_toks 128, stop at </s>. Official CodeXGLUE tasks use task-specific metrics (accuracy, MAP, CodeBLEU, BLEU, EM) and often hold out test labels for email submission.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub