LiveCodeBench v-5

LiveCodeBench v-5 is a benchmark dataset used to evaluate the performance of code language models in competitive programming tasks, focusing on aspects such as task solvability, solution correctness, and test accuracy.

Papers using LiveCodeBench v-5 (4)

X-Coder: Advancing Competitive Programming with Fully Synthetic Tasks, Solutions, and Tests2026Critique-Coder: Enhancing Coder Models by Critique Reinforcement Learning2025Critique-Coder: Enhancing Coder Models by Critique Reinforcement Learning2025PromptCoT 2.0: Scaling Prompt Synthesis for Large Language Model Reasoning2025