{
  "id": "gaia2",
  "name": "Gaia2",
  "category": "information",
  "summary": "CC-BY-4.0 follow-up to GAIA: 800 dynamic, time-aware agent scenarios released on Hugging Face and run with Meta’s ARE framework.",
  "description": "Established 2025 benchmark (Hugging Face dataset meta-agents-research-environments/gaia2; card license cc-by-4.0; not presented as a brand-new 2026 launch). Follow-up to the original GAIA benchmark already listed as gaia-benchmark. Scenarios run in Meta Agents Research Environments (ARE), listed separately. The dataset card describes 800 validation scenarios that test execution, search, adaptability, time, ambiguity, agent-to-agent collaboration, and noise in environments where time flows and events can arrive. dataset_info lists five capability configs (adaptability, ambiguity, execution, search, time) with 160 validation examples each (800 total), plus a demo split of 3 and a mini config of 160 validation examples. The same card's prose also calls mini “200 representative scenarios”; that count difference is recorded, not resolved. Card wording: the data is released CC-by 4.0 “and is intended for benchmarking purposes only.” Synthetic portions are outputs of Llama 3.3 and Llama 4 Maverick and remain subject to those Llama licenses, including a naming requirement if that portion is used to create, train, fine-tune, or otherwise improve a distributed AI model (the name must begin with “Llama”). Third-party content keeps its own licenses. The card states scenarios use fictional/simulated user data and that no real PII is intentionally included. A multilingual extension, facebook/omnilingual-gaia2, is pointed to from the ARE README and was not separately inventoried here. Running the official evaluator uses the ARE package and typically a model API — no keys or runs were used.",
  "url": "https://huggingface.co/datasets/meta-agents-research-environments/gaia2",
  "repo": "https://github.com/facebookresearch/meta-agents-research-environments",
  "docs": "https://facebookresearch.github.io/meta-agents-research-environments/user_guide/gaia2_evaluation.html",
  "tags": [
    "benchmark",
    "agent-evaluation",
    "dataset",
    "gaia",
    "open-source"
  ],
  "license": "CC-BY-4.0",
  "pricing": "open-source",
  "agent_access": {
    "auth": "none",
    "notes": "Public Hugging Face dataset. Official runs go through the ARE package (pip install meta-agents-research-environments). No download-gated access was encountered; no evaluation was executed."
  },
  "related": [
    "gaia-benchmark",
    "meta-agents-research-environments"
  ],
  "sources": [
    "https://huggingface.co/datasets/meta-agents-research-environments/gaia2",
    "https://huggingface.co/datasets/meta-agents-research-environments/gaia2/raw/main/README.md",
    "https://huggingface.co/blog/gaia2",
    "https://facebookresearch.github.io/meta-agents-research-environments/user_guide/gaia2_evaluation.html",
    "https://github.com/facebookresearch/meta-agents-research-environments"
  ],
  "maintainer": "Meta / facebookresearch",
  "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/gaia2/",
    "markdown": "https://indexagentica.com/entries/gaia2.md",
    "json": "https://indexagentica.com/api/entries/gaia2.json",
    "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/gaia2.json"
  }
}
