Geographic knowledge benchmark for geospatial AI
How well AI models do geographic knowledge on satellite, aerial and map data: 1 set with results, scored the same way for every model.
Sets
| Set | Index | Tasks of this type | Best score on the set | Models |
|---|---|---|---|---|
| Geospatial knowledge | Spatial Intelligence Index | all | 95 | 42 |
Top models
Best score on Geospatial knowledge, the set most models have run, 0 to 100.
| Rank | Model | Developer | Score |
|---|---|---|---|
| 1 | Claude Opus 5.5 | Anthropic | 95 |
| 2 | Claude Sonnet 5.5 | Anthropic | 94 |
| 3 | Gemini 3.8 Flash | 94 | |
| 4 | Claude Opus 4.8 | Anthropic | 93 |
| 5 | Claude Opus 5 | Anthropic | 93 |
| 6 | Nemotron 3.5 Super 120B | NVIDIA | 93 |
| 7 | Claude Opus 4.7 | Anthropic | 93 |
| 8 | GPT-6.1 Sol | OpenAI | 93 |
| 9 | GPT-5.6 Sol | OpenAI | 93 |
| 10 | GPT-5.6 Terra | OpenAI | 92 |
Every task type · Every evaluation · Methodology
Frequently asked questions
Which AI model is best at geographic knowledge on geospatial data?
Claude Opus 5.5 leads, on the sets below. Best score on Geospatial knowledge, the set most models have run, 0 to 100.
What is this geographic knowledge benchmark?
Every task in our sets that asks for geographic knowledge, 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.
