{
  "id": "ifeval",
  "code": "PTL-0208",
  "term": "IFEval",
  "aliases": [
    "Instruction-Following Eval"
  ],
  "category": "benchmarks",
  "definition": "IFEval (Instruction-Following Eval) is a benchmark of prompts containing instructions whose compliance can be checked automatically, such as \"write at least 300 words\" or \"do not use any commas\", used to measure instruction following without a human or model judge.",
  "description": "Verifiable instructions make scoring objective and cheap, which is why IFEval is a common headline score for instruction-tuned models. It measures adherence to format and content constraints, not answer quality.",
  "example": null,
  "broader": [
    "benchmark"
  ],
  "narrower": [],
  "related": [
    "instruction-following",
    "mt-bench"
  ],
  "introduced": 2023,
  "added": "2026-10-10",
  "sources": [
    {
      "title": "Instruction-Following Evaluation for Large Language Models",
      "authors": "Zhou et al.",
      "year": 2023,
      "url": "https://arxiv.org/abs/2311.07911"
    }
  ],
  "url": "https://protologue.com/t/ifeval/",
  "citation": "Protologue. (2026). IFEval. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0208). https://protologue.com/t/ifeval/"
}