Skip to content

LINGO LABSIIT Gandhinagar

Benchmark

PythonSaga

Benchmark for evaluating code-generating large language models.

Theme: Evaluation, Reliability & Trustworthy AI
Type: Benchmark
Funding: Unfunded

Paper and data

PythonSaga: Redefining the Benchmark to Evaluate Code Generating LLMs

Yadav, Beniwal, Singh. Findings of EMNLP 2024.

Paper arXiv GitHub Hugging Face

Theme →Datasets and models →Publications →