EvalPlus

Evalplus is a benchmark dataset used to evaluate the performance of code generation models, specifically focusing on their ability to generate code while preserving privacy and security.

Papers using EvalPlus (8)

LLM-Powered Test Case Generation for Detecting Bugs in Plausible Programs2024 · 3 citesUnify and Triumph: Polyglot, Diverse, and Self-Consistent Generation of Unit Tests with LLMs2025 · 1 citesBeyond Translation Accuracy: Addressing False Failures in LLM-Based Code Translation2026NOIR: Privacy-Preserving Generation of Code with Open-Source LLMs2026OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement2024 · 4 citesLow-Cost Language Models: Survey and Performance Evaluation on Python Code Generation2024 · 2 citesTowards Large Language Model Aided Program Refinement2024 · 1 citesBeyond Code Generation: Assessing Code LLM Maturity with Postconditions2024