{
  "artifactKind": "Benchmark",
  "definition": "A benchmark for evaluating browsing agents on their ability to locate hard-to-find information on the web and produce short, verifiable answers.",
  "derivedRelations": [
    {
      "note": "BrowseComp is a benchmark for evaluating browsing agents; a web browsing agent is the system being evaluated.",
      "target": "web-browsing-agent",
      "type": "notEquivalentTo"
    }
  ],
  "distinctions": [
    {
      "reason": "BrowseComp evaluates browsing agents finding hard-to-locate web information; BEIR is a fixed information-retrieval benchmark suite.",
      "statement": "BrowseComp is not BEIR.",
      "target": "beir",
      "targetLabel": "BEIR",
      "targetUri": "https://id.searchplex.net/beir/"
    },
    {
      "reason": "BrowseComp evaluates browsing agents in live web conditions; BrowseComp-Plus derives from BrowseComp but uses a fixed curated corpus, supporting documents, and hard negatives for controlled evaluation.",
      "statement": "BrowseComp is not BrowseComp-Plus.",
      "target": "browsecomp-plus",
      "targetLabel": "BrowseComp-Plus",
      "targetUri": "https://id.searchplex.net/browsecomp-plus/"
    },
    {
      "reason": "BrowseComp is a browsing-agent benchmark; a test collection is a fixed IR evaluation resource consisting of corpus, topics or queries, and relevance judgments.",
      "statement": "BrowseComp is not Test Collection.",
      "target": "test-collection",
      "targetLabel": "Test Collection",
      "targetUri": "https://id.searchplex.net/test-collection/"
    }
  ],
  "id": "browsecomp",
  "kind": "Artifact",
  "license": "https://creativecommons.org/publicdomain/zero/1.0/",
  "links": [
    {
      "label": "BrowseComp",
      "type": "officialHomepage",
      "url": "https://openai.com/index/browsecomp/"
    },
    {
      "label": "BrowseComp paper",
      "type": "definingReference",
      "url": "https://arxiv.org/abs/2504.12516"
    },
    {
      "label": "OpenAI simple-evals",
      "type": "officialRepository",
      "url": "https://github.com/openai/simple-evals"
    }
  ],
  "modifiedAt": "2026-09-14T06:43:46Z",
  "prefLabel": "BrowseComp",
  "publisher": {
    "name": "Searchplex",
    "url": "https://searchplex.net/"
  },
  "relations": [
    {
      "target": "deep-research",
      "type": "evaluates"
    },
    {
      "target": "web-browsing-agent",
      "type": "evaluates"
    },
    {
      "target": "web-browsing-agent-evaluation",
      "type": "evaluates"
    },
    {
      "note": "BrowseComp evaluates browsing agents finding hard-to-locate web information; BEIR is a fixed information-retrieval benchmark suite.",
      "target": "beir",
      "type": "notEquivalentTo"
    },
    {
      "note": "BrowseComp evaluates browsing agents in live web conditions; BrowseComp-Plus derives from BrowseComp but uses a fixed curated corpus, supporting documents, and hard negatives for controlled evaluation.",
      "target": "browsecomp-plus",
      "type": "notEquivalentTo"
    },
    {
      "note": "BrowseComp is a browsing-agent benchmark; a test collection is a fixed IR evaluation resource consisting of corpus, topics or queries, and relevance judgments.",
      "target": "test-collection",
      "type": "notEquivalentTo"
    },
    {
      "target": "agentic-retrieval",
      "type": "related"
    },
    {
      "target": "browsecomp-plus",
      "type": "related"
    },
    {
      "target": "deep-research",
      "type": "related"
    },
    {
      "target": "web-browsing-agent",
      "type": "related"
    },
    {
      "target": "web-browsing-agent-evaluation",
      "type": "related"
    },
    {
      "target": "web-search",
      "type": "related"
    }
  ],
  "representations": {
    "html": "https://id.searchplex.net/browsecomp/",
    "json": "https://id.searchplex.net/browsecomp.json",
    "jsonld": "https://id.searchplex.net/browsecomp.jsonld"
  },
  "scheme": "https://id.searchplex.net/scheme/",
  "scopeNote": "BrowseComp evaluates web-browsing agent behavior over live web search and browsing conditions. It is not a fixed IR test collection in the BEIR sense and should be distinguished from BrowseComp-Plus, which introduces a fixed curated corpus for more controlled evaluation.",
  "status": "published",
  "uri": "https://id.searchplex.net/browsecomp/"
}