Axis Spatial Spatial Intelligence Index

Search modelsMenu

Spatial SQL benchmark for geospatial AI

How well AI models do spatial sql on satellite, aerial and map data: 3 sets with results, scored the same way for every model.

Sets

Spatial SQL: sets that cover it
SetIndexTasks of this typeBest score on the setModels
GS-QA2Spatial Agent Indexall9448
GS-QA2 FullSpatial Agent Indexall889
GeoAgentEvalSpatial Agent Indexall10031

Top models

Mean of each model's best score on the 3 sets, 0 to 100, for the 9 models that have run all of them.

Top models on spatial sql
RankModelDeveloperScore
1Claude Opus 5.5Anthropic94
2Claude Sonnet 5.5Anthropic92
3Claude Opus 5Anthropic91
4Claude Haiku 5.5Anthropic88
5Claude Opus 4.8Anthropic85
6Claude Opus 4.7Anthropic83
7Claude Sonnet 5Anthropic82
8Claude Haiku 4.5Anthropic74
9Nemotron 3.5 Bolt E4BNVIDIA15

Every task type · Every evaluation · Methodology

Frequently asked questions

Which AI model is best at spatial sql on geospatial data?
Claude Opus 5.5 leads, on the sets below. Mean of each model's best score on the 3 sets, 0 to 100, for the 9 models that have run all of them.
What is this spatial sql benchmark?
Every task in our sets that asks for spatial sql, in GIS and Earth observation work, with each set's own score. It is a view over the sets, not an index of its own.
Which index does it count in?
Each set counts in one index: the Spatial Agent Index, as the table shows.