LiveCodeBench v-5

'LiveCodeBench v-5' is a benchmark dataset that contains a variety of programming tasks used to evaluate the reasoning capabilities of large language models in competitive programming contexts.

Papers using LiveCodeBench v-5 (3)

Semantic Flow Regularization: Teaching LLMs to Generate Diverse Yet Coherent Responses2026X-Coder: Advancing Competitive Programming with Fully Synthetic Tasks, Solutions, and Tests2026PromptCoT 2.0: Scaling Prompt Synthesis for Large Language Model Reasoning2025