SAR and InSAR benchmark for geospatial AI
How well AI models do sar and insar on satellite, aerial and map data: 2 sets with results, scored the same way for every model.
Sets
| Set | Index | Tasks of this type | Best score on the set | Models |
|---|---|---|---|---|
| BigEarthNet.txt | Spatial Intelligence Index | 120 | 60 | 16 |
| InSAR Regional Snow Mapping | Spatial Agent Index | all | 100 | 17 |
Top models
Mean of each model's best score on the 2 sets, 0 to 100, for the 14 models that have run all of them.
| Rank | Model | Developer | Score |
|---|---|---|---|
| 1 | Claude Opus 5.5 | Anthropic | 80 |
| 2 | Claude Sonnet 5.5 | Anthropic | 79 |
| 3 | Claude Haiku 5.5 | Anthropic | 77 |
| 4 | Claude Opus 5 | Anthropic | 77 |
| 5 | Claude Opus 4.7 | Anthropic | 74 |
| 6 | Step 5 Preview | StepFun | 74 |
| 7 | Claude Opus 4.8 | Anthropic | 74 |
| 8 | Qwen 3.8 27B | Alibaba (Qwen) | 74 |
| 9 | Claude Sonnet 5 | Anthropic | 73 |
| 10 | Nemotron 3.5 Super VL 120B | NVIDIA | 73 |
Every task type · Every evaluation · Methodology
Frequently asked questions
Which AI model is best at sar and insar on geospatial data?
Claude Opus 5.5 leads, on the sets below. Mean of each model's best score on the 2 sets, 0 to 100, for the 14 models that have run all of them.
What is this sar and insar benchmark?
Every task in our sets that asks for sar and insar, 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.
