Axis Spatial Spatial Intelligence Index

Search modelsMenu

Object counting benchmark for geospatial AI

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

Sets

Object counting: sets that cover it
SetIndexTasks of this typeBest score on the setModels
Vision (no tools)Spatial Intelligence Index1895924
BigEarthNet.txtSpatial Intelligence Index406016
Vision agentsSpatial Agent Indexall9420

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 object counting
RankModelDeveloperScore
1Claude Opus 5.5Anthropic71
2Claude Sonnet 5.5Anthropic67
3Claude Opus 5Anthropic61
4Claude Haiku 5.5Anthropic60
5Claude Opus 4.8Anthropic55
6Claude Sonnet 5Anthropic55
7Claude Opus 4.7Anthropic54
8Qwen 3.8 27BAlibaba (Qwen)46
9Claude Haiku 4.5Anthropic32

Every task type · Every evaluation · Methodology

Frequently asked questions

Which AI model is best at object counting 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 object counting benchmark?
Every task in our sets that asks for object counting, 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 or the Spatial Intelligence Index, as the table shows.