Spatial Reasoning over Optical/SAR Imagery on ThinkGeo
87.05Perception F1 ScoreGPT-4o
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| GPT-4o2026.01 | 87.05 | 76.68 | 67.88 | 11.51 | 20.02 | |
| Claude-3.7-Sonnet2026.01 | 85.16 | 85.93 | 64.41 | 8.95 | 11.42 | |
| GeoEvolverBackbone=GPT-4o-mini2026.01 | 83.9 | 90.5 | 79.03 | 46.88 | 53.74 | |
| GPT-4-11062026.01 | 79.91 | 69.15 | 56.29 | 9.46 | 16.91 | |
| Qwen3-8B2026.01 | 59.45 | 70.37 | 33.53 | 7.67 | 8.68 |