HumanEval-X

CodeGeeX's multilingual HumanEval: 820 hand-crafted problems across Python, C++, Java, JavaScript and Go, extending the same 164 tasks by hand rather than by machine translation.

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
Subcategorymultilingual code generation
Page statusactive
Metricpass@1
Directionhigher_is_better
Unit%
Dataset size820
Dataset licenceApache-2.0
PublisherTsinghua University; Zhipu.AI; Huawei

What it measures

HumanEval-X measures whether a code model's ability transfers beyond Python by hand-crafting the same underlying problems in four more languages. For each of HumanEval's 164 tasks, CodeGeeX's authors wrote an equivalent declaration, docstring, canonical solution and test suite in C++, Java, JavaScript and Go, alongside the existing Python version, for 820 problems in total. Two tasks are supported: code generation, where the model sees a declaration and docstring and must produce the solution, and code translation, where the model sees declarations in two languages plus a solution in one and must produce the equivalent solution in the other.

Task format

Given a function declaration and docstring in the target language, generate the function body (code generation); or given declarations in two languages and a solution in the source language, generate the equivalent solution in the target language, with the natural-language description removed (code translation). Both are graded by executing against per-language unit tests (pass@k).

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub