{
  "schema_version": "rangoon.article.v1",
  "id": "https://rangoon.ai/insights/archive-openai-browsecomp-browsing-agent-benchmark-april-2025/",
  "url": "https://rangoon.ai/insights/archive-openai-browsecomp-browsing-agent-benchmark-april-2025/",
  "markdown_url": "https://rangoon.ai/insights/archive-openai-browsecomp-browsing-agent-benchmark-april-2025/index.md",
  "json_url": "https://rangoon.ai/insights/archive-openai-browsecomp-browsing-agent-benchmark-april-2025/index.json",
  "title": "OpenAI released BrowseComp for hard-to-find web information tasks",
  "summary": "OpenAI released BrowseComp on April 10, 2025, with 1,266 short-answer tasks designed to test persistent web browsing and verification.",
  "language": "en",
  "author": {
    "name": "Rangoon Editorial",
    "url": "https://rangoon.ai/insights/editorial/"
  },
  "publisher": {
    "name": "Rangoon",
    "maintainer": "Hypler",
    "url": "https://rangoon.ai/"
  },
  "format": "News analysis",
  "topic": {
    "slug": "agents",
    "label": "Agent systems",
    "url": "https://rangoon.ai/insights/topics/agents/"
  },
  "tags": [
    {
      "slug": "openai",
      "label": "OpenAI",
      "url": "https://rangoon.ai/insights/tags/openai/"
    },
    {
      "slug": "ai-evaluation",
      "label": "AI evaluation",
      "url": "https://rangoon.ai/insights/tags/ai-evaluation/"
    },
    {
      "slug": "agent-benchmarks",
      "label": "agent benchmarks",
      "url": "https://rangoon.ai/insights/tags/agent-benchmarks/"
    },
    {
      "slug": "browser-agents",
      "label": "browser agents",
      "url": "https://rangoon.ai/insights/tags/browser-agents/"
    }
  ],
  "dates": {
    "published": "2026-10-24",
    "updated": "2026-10-24",
    "event": "2025-04-10"
  },
  "event_source_id": 1,
  "retrospective": true,
  "reading_minutes": 3,
  "takeaways": [
    "BrowseComp separated hard-to-find fact location from broad, open-ended question answering.",
    "Short answers made checking practical while narrowing what the benchmark represents.",
    "Model results depend on browsing policy, search state, tool access, samples and the protected task set."
  ],
  "source_note": "Historical reporting: OpenAI released BrowseComp on April 10, 2025 and said the open benchmark contained 1,266 hard-to-find, short-answer browsing problems. The release describes model screening, search-result checks, human verification and explicit limits around open-ended user queries. Its linked simple-evals repository is the public implementation context. OpenAI’s model results and test-time-compute experiments are supplier records on BrowseComp; they do not prove general research quality, citation reliability, safe browsing or performance on a changing live web.",
  "sources": [
    {
      "id": 1,
      "title": "OpenAI: BrowseComp launch",
      "url": "https://openai.com/index/browsecomp/",
      "published": "2025-04-10"
    },
    {
      "id": 2,
      "title": "OpenAI: simple-evals BrowseComp implementation",
      "url": "https://github.com/openai/simple-evals",
      "published": null
    }
  ],
  "image": {
    "url": "https://rangoon.ai/assets/editorial/archive-openai-browsecomp-browsing-agent-benchmark-april-2025-diagram-v1.webp",
    "thumbnail_url": "https://rangoon.ai/assets/editorial/archive-openai-browsecomp-browsing-agent-benchmark-april-2025-diagram-v1-thumb.webp",
    "alt": "Original evaluation explanatory diagram, Hard-to-find clue routed to checked short answer. Labels: Clue, Search, Sources, Reasoning, Answer, Check. Source boundary: dated primary release reporting; original editorial analysis.",
    "type": "original-diagram",
    "caption": "Hard-to-find clue routed to checked short answer. Original Rangoon explanatory diagram: Source boundary: dated primary release reporting; original editorial analysis. No vendor interface, photograph, measurement result, or endorsement implied.",
    "credit": "Rangoon / Hypler",
    "source_url": "https://rangoon.ai/brand/",
    "rights_url": "https://rangoon.ai/terms/#media-use",
    "rights_note": "Hypler artwork permissions do not grant rights to third-party marks or imply endorsement."
  },
  "sections": [
    {
      "id": "april-release",
      "url": "https://rangoon.ai/insights/archive-openai-browsecomp-browsing-agent-benchmark-april-2025/#april-release",
      "heading": "OpenAI released 1,266 browsing tasks on April 10, 2025",
      "paragraphs": [
        "OpenAI dated BrowseComp to April 10, 2025 and described an open-source benchmark of 1,266 challenging problems for agents locating hard-to-find information online. The release’s premise is deliberate: a useful browsing agent may need to connect clues across many sites, not merely retrieve a familiar fact. BrowseComp restricts answers to short, single-answer targets so they can be checked. That makes the event a release of a defined browsing evaluation, not a release of a general web-research certification. A task can be difficult to locate and easy to verify while still differing sharply from a reader’s ambiguous, multi-part or time-sensitive request."
      ],
      "bullets": [],
      "source_ids": [
        1
      ]
    },
    {
      "id": "construction",
      "url": "https://rangoon.ai/insights/archive-openai-browsecomp-browsing-agent-benchmark-april-2025/#construction",
      "heading": "The construction process filtered for questions that were hard to find but bounded to grade",
      "paragraphs": [
        "OpenAI says trainers created questions from evidence-backed facts, then used checks involving contemporary models, simple searches and human attempts to assess difficulty. The release calls this an asymmetry of verification: finding an answer can require broad exploration, while checking a proposed short answer can be direct. That design gives BrowseComp a clear grading target, but it also sets a boundary on the conclusion. It does not evaluate whether an agent writes a useful explanation, handles a disputed source, asks a clarifying question, maintains citations or decides that a query is unsafe. The exact task-writing and filtering process is part of what a BrowseComp score represents."
      ],
      "bullets": [],
      "source_ids": [
        1
      ]
    },
    {
      "id": "conditions",
      "url": "https://rangoon.ai/insights/archive-openai-browsecomp-browsing-agent-benchmark-april-2025/#conditions",
      "heading": "Tool use and inference-time effort were explicit conditions in OpenAI’s reported runs",
      "paragraphs": [
        "The launch compares models with and without browsing and describes experiments that vary browsing effort and aggregate repeated attempts. It reports that additional test-time work affected outcomes, while also noting that the Deep Research model was trained on data aimed at BrowseComp-style tasks. Those facts make it misleading to treat the numbers as attributes of a base model alone. The agent policy, model version, browser capabilities, search availability, maximum effort, number of samples and aggregation rule all help produce a run. A result obtained on the 2025 collection may also become less comparable as the live web changes, sources disappear or benchmark examples leak into training material."
      ],
      "bullets": [],
      "source_ids": [
        1,
        2
      ]
    },
    {
      "id": "retrieval-measure",
      "url": "https://rangoon.ai/insights/archive-openai-browsecomp-browsing-agent-benchmark-april-2025/#retrieval-measure",
      "heading": "BrowseComp measures hard answer retrieval while deliberately separating it from open-ended browsing help",
      "paragraphs": [
        "BrowseComp was designed around a particular asymmetry: locating a fact may require searching many sources, while verifying a proposed short answer can remain direct. OpenAI therefore used short, in-principle single-answer questions instead of long responses or disputed conclusions, and it says the benchmark does not aim to measure a common user-query distribution. This makes its 1,266 tasks suited to probing persistent clue-driven retrieval, not to scoring every part of a browsing assistant. The release also compares browsing policies, test-time effort and aggregation of repeated attempts, so a result belongs to an agent configuration as well as a model. Reading the benchmark this way preserves its method: it is evidence about controlled retrieval under its task construction, not a generic score for explanation quality or source judgment."
      ],
      "bullets": [],
      "source_ids": [
        1
      ]
    }
  ],
  "project_context": null,
  "related_links": [],
  "permissions_url": "https://rangoon.ai/permissions.txt",
  "content_hash": "sha256:c12e05585ace8d524efdf9b9b583e16cad523947a832f50ff9d6a22eed495585"
}