Axis Spatial Spatial Intelligence Index

Search modelsMenu

Distance and bearing benchmark for geospatial AI

How well AI models do distance and bearing on satellite, aerial and map data: 5 sets with results, scored the same way for every model.

Sets

Distance and bearing: sets that cover it
SetIndexTasks of this typeBest score on the setModels
GPSBench closed bookSpatial Intelligence Indexall939
Place and coordinate tasks, closed bookSpatial Intelligence Indexall9222
GS-QA2Spatial Agent Index259448
GS-QA2 FullSpatial Agent Index480889
Place and coordinate tasksSpatial Agent Indexall10013

Top models

Best score on GS-QA2, the set most models have run, 0 to 100.

Top models on distance and bearing
RankModelDeveloperScore
1Claude Opus 5.5Anthropic94
2GPT-6.1 SolOpenAI94
3Claude Sonnet 5.5Anthropic92
4Claude Opus 5Anthropic91
5Claude Fable 5.1Anthropic90
6DeepSeek V4.1 FlashDeepSeek89
7GPT-6 SolOpenAI89
8Claude Haiku 5.5Anthropic87
9GPT-5.6 SolOpenAI87
10Gemini 3.8 FlashGoogle86

Every task type · Every evaluation · Methodology

Frequently asked questions

Which AI model is best at distance and bearing on geospatial data?
Claude Opus 5.5 leads, on the sets below. Best score on GS-QA2, the set most models have run, 0 to 100.
What is this distance and bearing benchmark?
Every task in our sets that asks for distance and bearing, 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.