{
  "id": "agenticdatabench",
  "name": "AgenticDataBench",
  "category": "information",
  "summary": "Benchmark for data-science agents: 344 tasks over 97 real datasets in 15 domains, with 433 fine-grained skill labels for skill-level scoring.",
  "description": "From Tsinghua University and Ant Digital Technologies (arXiv 2607.01647). Domains include real B2B fintech use cases; tasks are built on 97 datasets. 98 tasks are withheld as a private test set for leaderboard integrity, to be released once the benchmark loses its evaluation significance. v1.1 released 2026-10-12. Baselines run on agent frameworks including smolagents; results are submitted by email. Code Apache-2.0; datasets Apache-2.0 on Hugging Face (shawnzzzh/AgenticDataBench).",
  "url": "https://agenticdatabench.github.io/",
  "repo": "https://github.com/AgenticDataBench/AgenticDataBench",
  "tags": [
    "benchmark",
    "data-agents",
    "data-science",
    "skills",
    "dataset"
  ],
  "license": "Apache-2.0",
  "pricing": "free",
  "status": "active",
  "sources": [
    "https://agenticdatabench.github.io/",
    "https://github.com/AgenticDataBench/AgenticDataBench",
    "https://huggingface.co/datasets/shawnzzzh/AgenticDataBench",
    "https://arxiv.org/abs/2607.01647"
  ],
  "added": "2026-11-04",
  "updated": "2026-11-04",
  "last_verified": "2026-11-04",
  "submitted_by": "agentica-curator",
  "maintainer": "AgenticDataBench (Tsinghua University, Ant Digital Technologies)",
  "longform": [],
  "links": {
    "html": "https://indexagentica.com/entries/agenticdatabench/",
    "markdown": "https://indexagentica.com/entries/agenticdatabench.md",
    "json": "https://indexagentica.com/api/entries/agenticdatabench.json",
    "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/agenticdatabench.json"
  }
}