A good score shows
Trajectory and final outcome evaluation for spatiotemporal reasoning using MCP-style EO tools.
Geospatial agent benchmark · none
Earth-Bench / Earth-Agent
Also known as: Earth-Bench, Earth-Agent
Evaluates: models with tool access
Trajectory and final outcome evaluation for spatiotemporal reasoning using MCP-style EO tools.
At a glance
pending verificationTasks
UnclearAgents run real code
NoData + code public
YesChecked by recomputation
—Data licence
Sources
every claim on this page traces to these records- Source paper: not published, or not yet verified — we do not guess URLs
- Source data: not published, or not yet verified — we do not guess URLs
- Source code: not published, or not yet verified — we do not guess URLs
- Leaderboard: not published, or not yet verified — we do not guess URLs
In shortWhether agents run real code here is not confirmed from public sources, and answers are checked by recomputation, not by another model's opinion. The underlying data and code are not published at a verified link. Product proof objects for user-produced spatial work. Research framework, not a production verification contract.
Evidence boundaries
what a score on this benchmark does and does not tell youA good score does not show
Product proof objects for user-produced spatial work. Research framework, not a production verification contract.
Arena status
none — Not downloaded. Identified in Axis geospatial verification gap research as an MCP-style EO tool and trajectory or final outcome evaluation framework for spatiotemporal reasoning. Deeper fields pending verification pending source review.
All recorded facts (22 fields)
- Evaluates
- model+tools
- Task families
- spatiotemporal reasoning,MCP-style EO tools
- Task count
- pending verification
- Difficulty
- pending verification
- Geography
- pending verification
- Modality
- mixed
- Input types
- EO data,MCP-style tool calls
- Output types
- trajectory outcomes,final outcomes
- Execution environment
- MCP-style EO tool environment (pending verification)
- Ground truth method
- pending verification
- Verifier method
- trajectory and final outcome evaluation for spatiotemporal reasoning
- Deterministic verification
- yes
- Scoring dimensions
- trajectory evaluation,final outcome evaluation
- Aggregation formula
- pending verification
- Trials policy
- pending verification
- Variance reporting
- pending verification
- Data licence
- pending verification
- Code licence
- pending verification
- Contamination concerns
- pending verification
- Reproducibility status
- pending verification (described as a research framework, not a product)
- First published
- 2026
- Latest known update
- pending verification
Machine-readable record
This entry is available as JSON at /api/registry#earth-bench-earth-agent. See the registry endpoint.