The paper proposes LiveCodeBench, which it describes as a comprehensive and contamination-free evaluation of LLMs for code that continuously collects new problems from contests on LeetCode, AtCoder and CodeForces.
One recorded claim. The claim panel gives its qualification, the source passages with their place in each source, and how it was checked.
What it connects
LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code → states its contribution → The paper proposes LiveCodeBench, which it describes as a comprehensive and contamination-free evaluation of LLMs for code that continuously collects new problems from contests on LeetCode, AtCoder and CodeForces.
Where it appears
No collection page holds this claim. It is listed with its records in the explorer.