Axis Spatial Spatial Intelligence Index

Search modelsMenu

GIS analysis benchmark for geospatial AI

How well AI models do gis analysis on satellite, aerial and map data: 6 sets with results, scored the same way for every model.

Sets

GIS analysis: sets that cover it
SetIndexTasks of this typeBest score on the setModels
GeoBenchXSpatial Agent Indexall8450
GeoAgentBenchSpatial Agent Indexall10050
OGD4AllSpatial Agent Indexall9730
GeoAgentEvalSpatial Agent Indexall10031
GeoNatureAgentSpatial Agent Indexall10026
GeoAnalystBenchSpatial Agent Indexall10050

Top models

Mean of each model's best score on the 6 sets, 0 to 100, for the 26 models that have run all of them.

Top models on gis analysis
RankModelDeveloperScore
1Claude Opus 5.5Anthropic97
2Claude Sonnet 5.5Anthropic96
3Claude Haiku 5.5Anthropic95
4GLM-5.3-FlashZ.ai93
5Claude Sonnet 5Anthropic93
6Claude Opus 4.8Anthropic93
7Claude Opus 5Anthropic93
8Kimi K3Moonshot AI92
9Claude Opus 4.7Anthropic92
10DeepSeek V4.1 FlashDeepSeek91

Every task type · Every evaluation · Methodology

Frequently asked questions

Which AI model is best at gis analysis on geospatial data?
Claude Opus 5.5 leads, on the sets below. Mean of each model's best score on the 6 sets, 0 to 100, for the 26 models that have run all of them.
What is this gis analysis benchmark?
Every task in our sets that asks for gis analysis, 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.