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
| Set | Index | Tasks of this type | Best score on the set | Models |
|---|---|---|---|---|
| GPSBench closed book | Spatial Intelligence Index | all | 93 | 9 |
| Place and coordinate tasks, closed book | Spatial Intelligence Index | all | 92 | 22 |
| GS-QA2 | Spatial Agent Index | 25 | 94 | 48 |
| GS-QA2 Full | Spatial Agent Index | 480 | 88 | 9 |
| Place and coordinate tasks | Spatial Agent Index | all | 100 | 13 |
Top models
Best score on GS-QA2, the set most models have run, 0 to 100.
| Rank | Model | Developer | Score |
|---|---|---|---|
| 1 | Claude Opus 5.5 | Anthropic | 94 |
| 2 | GPT-6.1 Sol | OpenAI | 94 |
| 3 | Claude Sonnet 5.5 | Anthropic | 92 |
| 4 | Claude Opus 5 | Anthropic | 91 |
| 5 | Claude Fable 5.1 | Anthropic | 90 |
| 6 | DeepSeek V4.1 Flash | DeepSeek | 89 |
| 7 | GPT-6 Sol | OpenAI | 89 |
| 8 | Claude Haiku 5.5 | Anthropic | 87 |
| 9 | GPT-5.6 Sol | OpenAI | 87 |
| 10 | Gemini 3.8 Flash | 86 |
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.
