LiveCodeBench

'LiveCodeBench' is a dataset/benchmark used to evaluate the performance of code generation models, particularly in their ability to handle complex algorithmic tasks and iterative refinement strategies.

Papers using LiveCodeBench (36)

Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages2026REVES: REvision and VErification--Augmented Training for Test-Time Scaling2026Kimi k1.5: Scaling Reinforcement Learning with LLMs2025 · 11 citesSakana Fugu Technical Report2026DecompRL: Solving Harder Problems by Learning Modular Code Generation2026Code Correctness Is Linearly Decodable from LLM Hidden States Before Generation2026Inferring Code Correctness from Specification2026CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings2025 · 2 citesOpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs2025 · 1 citesACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization2026Bridging Online and Offline RL: Contextual Bandit Learning for Multi-Turn Code Generation2026Scaling Data Difficulty: Improving Coding Models via Reinforcement Learning on Fresh and Challenging Problems2026NGM: A Plug-and-Play Training-Free Memory Module for LLMs2026BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution2026Apriel-Reasoner: RL Post-Training for General-Purpose and Efficient Reasoning2026ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning2026IntentCoding: Amplifying User Intent in Code Generation2026Test-time Recursive Thinking: Self-Improvement without External Feedback2026LLMs Can Learn to Reason Via Off-Policy RL2026DreamPRM-Code: Function-as-Step Process Reward Model with Label Correction for LLM Coding2025Process Reward Models That Think2025Not All Correct Answers Are Equal: Why Your Distillation Source Matters2025Skywork Open Reasoner 1 Technical Report2025Inference-Time Hyper-Scaling with KV Cache Compression2025Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs2025ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases2025LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!2025Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinking2025OpenCodeReasoning: Advancing Data Distillation for Competitive Coding2025Which Data Attributes Stimulate Math and Code Reasoning? An Investigation via Influence Functions2025rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset2025Rethinking Verification for LLM Code Generation: From Generation to Testing2025OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique2025QueST: Incentivizing LLMs to Generate Difficult Problems2025Scaling Reasoning without Attention2025SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM2025