{
  "citation": "Xiao Liu, Zirui Wu, Xueqing Wu, Pan Lu, Kai-Wei Chang, Yansong Feng. Are LLMs Capable of Data-based Statistical and Causal Reasoning? Benchmarking Advanced Quantitative Reasoning with Data. Findings of the Association for Computational Linguistics: ACL 2024, pages 9215-9235.",
  "deviation_evidence": null,
  "doi": null,
  "excerpt": "ReAct-style Prompting ... Gemini-Pro ... 38.9",
  "independent": null,
  "item_set": "different",
  "kind": "leaderboard",
  "known_deviation": null,
  "licence": "CC BY-NC 4.0",
  "locator": "Table 2, ReAct-style Prompting, Gemini-Pro, Overall Acc.",
  "metric": "accuracy (eval.py), all 411 items",
  "n_items": 411,
  "page": "9219",
  "read_copy_sha256": "15e13f202cf232f3371e9ae1dc7f2d172f007c7bce4ac8e673c37f19a69856ff",
  "retrieved_at": "2026-10-15",
  "se": null,
  "se_as_published": null,
  "source_id": "qrdata.leaderboard.gemini_pro_react",
  "tolerance_reason": null,
  "units": "% accuracy",
  "url": "https://aclanthology.org/2024.findings-acl.548.pdf",
  "value": 38.9,
  "value_as_published": "38.9",
  "verified_by": "primary_source",
  "verified_note": "Accuracy over all 411 QRData items."
}