LiveCodeBench-v-6

LiveCodeBench-v-6 is a benchmark dataset used to evaluate code generation and reasoning capabilities, specifically focusing on the effectiveness of different strategies in achieving successful code outputs.

Papers using LiveCodeBench-v-6 (12)

SCOPE: Leveraging Subgoal Critiques for Code Generation2026Cast a Wider Net: Coordinated Pass@K Policy Optimization for Code Reasoning2026Primal Generation, Dual Judgment: Self-Training from Test-Time Scaling2026Embarrassingly Simple Self-Distillation Improves Code Generation2026Breaking Training Bottlenecks: Effective and Stable Reinforcement Learning for Coding Models2026BACE: LLM-based Code Generation through Bayesian Anchored Co-Evolution of Code and Test Populations2026Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters2026X-Coder: Advancing Competitive Programming with Fully Synthetic Tasks, Solutions, and Tests2026CoreThink: A Symbolic Reasoning Layer to reason over Long Horizon Tasks with LLMs2025PromptCoT 2.0: Scaling Prompt Synthesis for Large Language Model Reasoning2025Rethinking Verification for LLM Code Generation: From Generation to Testing2025PromptCoT 2.0: Scaling Prompt Synthesis for Large Language Model Reasoning2025