Axis Spatial Spatial Intelligence Index

Search modelsMenu

Visual question answering benchmark for geospatial AI

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

Sets

Visual question answering: sets that cover it
SetIndexTasks of this typeBest score on the setModels
Vision (no tools)Spatial Intelligence Indexall5924
BigEarthNet.txtSpatial Intelligence Indexall6016
GeoChronoSpatial Intelligence Indexall7616
GeoChrono larger setSpatial Intelligence Indexall695
DVL-BenchSpatial Intelligence Indexall318

Top models

Best score on Vision (no tools), the set most models have run, 0 to 100.

Top models on visual question answering
RankModelDeveloperScore
1Claude Opus 5.5Anthropic59
2Claude Sonnet 5.5Anthropic59
3GPT-5.6 SolOpenAI58
4GPT-6 SolOpenAI56
5GPT-6.1 SolOpenAI56
6GPT-5.6 TerraOpenAI54
7Claude Opus 5Anthropic53
8Qwen 3.8 27BAlibaba (Qwen)53
9GPT-6 LunaOpenAI53
10Claude Haiku 5.5Anthropic52

Every task type · Every evaluation · Methodology

Frequently asked questions

Which AI model is best at visual question answering on geospatial data?
Claude Opus 5.5 leads, on the sets below. Best score on Vision (no tools), the set most models have run, 0 to 100.
What is this visual question answering benchmark?
Every task in our sets that asks for visual question answering, 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 Intelligence Index, as the table shows.