{
  "id": "gdpval",
  "name": "GDPval",
  "category": "information",
  "summary": "OpenAI benchmark of real-world, economically valuable knowledge-work tasks across 44 occupations; a 220-task gold subset with files and rubrics is open on Hugging Face.",
  "description": "The full set has 1,320 tasks built from real work products by professionals averaging 14 years of experience, spanning 44 occupations in the top 9 sectors of U.S. GDP. Each task has a prompt plus reference files (spreadsheets, documents, etc.); the open gold subset (`openai/gdpval`, v2 with rubrics and gold deliverables) has 220 tasks. OpenAI offers an experimental automated grader at evals.openai.com; human expert comparison remains the recommended grading method. Some tasks contain NSFW or political content. The Hugging Face dataset card does not state a license.",
  "url": "https://openai.com/index/gdpval/",
  "docs": "https://huggingface.co/datasets/openai/gdpval",
  "tags": [
    "benchmark",
    "knowledge-work",
    "dataset",
    "evals",
    "economics"
  ],
  "pricing": "free",
  "status": "active",
  "related": [
    "the-agent-company",
    "humanitys-last-exam",
    "metr-time-horizons"
  ],
  "sources": [
    "https://huggingface.co/datasets/openai/gdpval",
    "https://arxiv.org/abs/2510.04374",
    "https://openai.com/index/gdpval/"
  ],
  "added": "2026-10-26",
  "updated": "2026-10-26",
  "last_verified": "2026-10-26",
  "submitted_by": "agentica-curator",
  "maintainer": "OpenAI",
  "longform": [],
  "links": {
    "html": "https://indexagentica.com/entries/gdpval/",
    "markdown": "https://indexagentica.com/entries/gdpval.md",
    "json": "https://indexagentica.com/api/entries/gdpval.json",
    "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/gdpval.json"
  }
}