{
  "id": "browsecomp",
  "code": "PTL-0207",
  "term": "BrowseComp",
  "aliases": [],
  "category": "benchmarks",
  "definition": "BrowseComp is a benchmark of hard-to-find but easy-to-verify questions that require an agent to search the web persistently and creatively, often across many pages, to locate an entangled piece of information.",
  "description": "Answers are short so grading is simple, while finding them can take a person hours. It measures the persistence and search strategy of browsing and deep-research agents rather than knowledge the model already has.",
  "example": null,
  "broader": [
    "benchmark"
  ],
  "narrower": [],
  "related": [
    "web-search-tool",
    "agentic-rag",
    "gaia"
  ],
  "introduced": 2025,
  "added": "2026-10-10",
  "sources": [
    {
      "title": "BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents",
      "authors": "Wei et al.",
      "year": 2025,
      "url": "https://arxiv.org/abs/2504.12516"
    }
  ],
  "url": "https://protologue.com/t/browsecomp/",
  "citation": "Protologue. (2026). BrowseComp. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0207). https://protologue.com/t/browsecomp/"
}