{
  "id": "livecodebench",
  "code": "PTL-0201",
  "term": "LiveCodeBench",
  "aliases": [],
  "category": "benchmarks",
  "definition": "LiveCodeBench is a coding benchmark that continuously collects new problems from programming contests, such as LeetCode, AtCoder, and Codeforces, so that models can be evaluated only on problems published after their training data was collected.",
  "description": "Dating each problem lets evaluators detect and avoid data contamination. Besides code generation, it covers self-repair, predicting the output of code, and predicting test outputs.",
  "example": null,
  "broader": [
    "benchmark"
  ],
  "narrower": [],
  "related": [
    "data-contamination",
    "humaneval",
    "pass-at-k"
  ],
  "introduced": 2024,
  "added": "2026-10-10",
  "sources": [
    {
      "title": "LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code",
      "authors": "Jain et al.",
      "year": 2024,
      "url": "https://arxiv.org/abs/2403.07974"
    }
  ],
  "url": "https://protologue.com/t/livecodebench/",
  "citation": "Protologue. (2026). LiveCodeBench. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0201). https://protologue.com/t/livecodebench/"
}