{
  "id": "ruler",
  "code": "PTL-0211",
  "term": "RULER",
  "aliases": [],
  "category": "benchmarks",
  "definition": "RULER is a synthetic long-context benchmark that extends needle-in-a-haystack retrieval with harder tasks, such as multiple needles, multi-hop tracing, and aggregation, at configurable context lengths, to measure how much of its context window a model can actually use.",
  "description": "Its creators found that many models performed well on simple needle retrieval but degraded well before their advertised context length on the harder tasks. It is a standard reference for a model's effective, as opposed to claimed, context size.",
  "example": null,
  "broader": [
    "benchmark"
  ],
  "narrower": [],
  "related": [
    "needle-in-a-haystack",
    "context-window",
    "context-rot",
    "lost-in-the-middle"
  ],
  "introduced": 2024,
  "added": "2026-10-10",
  "sources": [
    {
      "title": "RULER: What's the Real Context Size of Your Long-Context Language Models?",
      "authors": "Hsieh et al.",
      "year": 2024,
      "url": "https://arxiv.org/abs/2404.06654"
    }
  ],
  "url": "https://protologue.com/t/ruler/",
  "citation": "Protologue. (2026). RULER. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0211). https://protologue.com/t/ruler/"
}