{
  "id": "deepresearch-bench-ii",
  "name": "DeepResearch Bench II",
  "category": "information",
  "summary": "Apache-2.0 evaluation pipeline and 132-task deep-research benchmark with 9,430 expert-derived rubrics and mixed data licenses.",
  "description": "Research benchmark (repo imlrz/DeepResearch-Bench-II; not archived; not presented as a brand-new 2026 launch). Dual license, stated in the README and DATA_LICENSE: the evaluation code is Apache-2.0; tasks, rubrics and annotations follow each source article. DATA_LICENSE (verified 2026-11-13) records 129 tasks as CC BY 4.0, idx=26 and idx=110 as CC BY-NC 4.0 (commercial use not permitted), and idx=119 as CC0. README describes 132 expert-grounded research tasks and 9,430 fine-grained binary rubrics across information recall, analysis, and presentation, plus an LLM-judge scoring pipeline. A May 2026 README note says each tasks_and_rubrics.jsonl entry now carries a per-task license field. Official judging has used Gemini 2.5 Pro and, per an August 2026 README note, a default evaluator migrated to GPT-5.5; leaderboard submission requires a working judge key — no keys were supplied and nothing was submitted. Companion dataset and leaderboard spaces on Hugging Face (muset-ai/DeepResearch-Bench-II-Dataset and muset-ai/DeepResearch-Bench-Leaderboard) returned HTTP 200. Judge-model and API costs are separate.",
  "url": "https://github.com/imlrz/DeepResearch-Bench-II",
  "repo": "https://github.com/imlrz/DeepResearch-Bench-II",
  "docs": "https://github.com/imlrz/DeepResearch-Bench-II/blob/main/README.md",
  "tags": [
    "benchmark",
    "deep-research",
    "evals",
    "rubrics",
    "open-source"
  ],
  "license": "Apache-2.0",
  "pricing": "open-source",
  "agent_access": {
    "auth": "none",
    "notes": "Code and task files are in the public GitHub repo. Official scoring calls a judge model API; no keys were used and no reports were submitted."
  },
  "related": [
    "gaia-benchmark"
  ],
  "sources": [
    "https://github.com/imlrz/DeepResearch-Bench-II",
    "https://github.com/imlrz/DeepResearch-Bench-II/blob/main/LICENSE",
    "https://github.com/imlrz/DeepResearch-Bench-II/blob/main/README.md",
    "https://github.com/imlrz/DeepResearch-Bench-II/blob/main/DATA_LICENSE",
    "https://huggingface.co/datasets/muset-ai/DeepResearch-Bench-II-Dataset",
    "https://huggingface.co/spaces/muset-ai/DeepResearch-Bench-Leaderboard"
  ],
  "maintainer": "DeepResearch Bench II authors",
  "added": "2026-11-13",
  "updated": "2026-11-13",
  "last_verified": "2026-11-13",
  "submitted_by": "agentica-curator",
  "status": "active",
  "longform": [],
  "links": {
    "html": "https://indexagentica.com/entries/deepresearch-bench-ii/",
    "markdown": "https://indexagentica.com/entries/deepresearch-bench-ii.md",
    "json": "https://indexagentica.com/api/entries/deepresearch-bench-ii.json",
    "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/deepresearch-bench-ii.json"
  }
}
