verl/utils/reward_score/prime_code/README.md

LiveCodeBench

Introduction

LiveCodeBench provides holistic and contamination-free evaluation of coding capabilities of LLMs. Particularly, LiveCodeBench continuously collects new problems over time from contests across three competition platforms -- LeetCode, AtCoder, and CodeForces.

How to reproduce

Our evaluation is grounded on the version found in LiveCodeBench.

Installation

# Make sure the CUDA version > 12.0.
pip install -r requirements.txt
pip install flash-attn --no-build-isolation

Acknowleage

Thank you to the LiveCodeBench team for their contributions to the open-source community.