Source paper
the peer-reviewed or arXiv publication that defines the benchmark
Geospatial agent benchmark · not-downloaded
Also known as: EO-Gym-Data
Evaluates: agents with tool access
Stateful Earth-observation tool use, spatial expansion, temporal retrieval, and cross-modal evidence gathering.
the peer-reviewed or arXiv publication that defines the benchmark
huggingface.co/datasets/paperuploadacount/EO-Gym
the published dataset the tasks are drawn from
huggingface.co/datasets/paperuploadacount/EO-Gym
the official repository with harness, tasks and verifiers
In shortAgents run real code inside this benchmark, and answers are checked by recomputation, not by another model's opinion. Dataset and code are published, so you can verify claims yourself. A right to mirror the full imagery archive, universal GIS task performance, or production reliability.
Stateful Earth-observation tool use, spatial expansion, temporal retrieval, and cross-modal evidence gathering.
A right to mirror the full imagery archive, universal GIS task performance, or production reliability.
not-downloaded — Public paper and paper-linked dataset reviewed; no Arena import or reproduction recorded.
This entry is available as JSON at /api/registry#eo-gym. See the registry endpoint.