GAIA

{
  "doc": "nguyen-2025-sfr-deepresearch.md",
  "context": "General assistant benchmark focusing on browsing tasks; SFR-DR-20B achieves 66.0% on text-only evaluation set.",
  "norm_label": "GAIA",
  "graphify_id": "gaia_benchmark",
  "source_file": "nguyen-2025-sfr-deepresearch.md",
  "imported_from": "/Users/antonborzov/Documents/Research.nosync/papers/extract_typed_out/nguyen-2025-sfr-deepresearch/graph.json",
  "extracted_type": "dataset",
  "source_location": "§4.1",
  "graphify_file_type": "dataset"
}