Geospatial Reasoning on GeoQA Hard
87.4R@1GPT-4o
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GPT-4o2026.05 | 87.4 | 88.1 | |
| GeoQA2026.05 | 74.8 | 81.8 | |
| Qwen2.5-14B2026.05 | 67.7 | 72.7 | |
| BM252026.05 | 33.3 | 71.7 | |
| DPR2026.05 | 16.2 | 25.3 |
Loading the SOTA2 catalog…
| Method | Links | ||
|---|---|---|---|
| GPT-4o2026.05 | 87.4 | 88.1 | |
| GeoQA2026.05 | 74.8 | 81.8 | |
| Qwen2.5-14B2026.05 | 67.7 | 72.7 | |
| BM252026.05 | 33.3 | 71.7 | |
| DPR2026.05 | 16.2 | 25.3 |