Scene Classification on WHU-RS19
99.5AccuracyGeoSolver
Evaluation results
| Method | Links | |
|---|---|---|
| GeoSolverModel Category=Ours2026.03 | 99.5 | |
| Earth-OneVision (2B)Input Images=12026.06 | 97.31 | |
| EarthDial (4B)Input Images=12026.06 | 96.21 | |
| EarthDialPublication=CVPR’252026.04 | 95.8 | |
| VHMPublication=AAAI’252026.04 | 95.8 | |
| ChatGPT-5Model Category=Closed-source Commercial Vision-Language Models2026.03 | 95.53 | |
| LHRS-BotPublication=ECCV’242026.04 | 93.17 | |
| SkySenseGPTModel Category=Open-source Remote Sensing Vision-Language Models2026.03 | 93.16 | |
| SkySenseGPT (7B)Input Images=12026.06 | 93.16 | |
| FUSE-RSVLMPublication=arXiv’252026.04 | 93.1 | |
| VHMModel Category=Open-source Remote Sensing Vision-Language Models2026.03 | 91.84 | |
| VHM (7B)Input Images=12026.06 | 91.84 | |
| InternVL3.5Publication=arXiv’252026.04 | 91.5 | |
| GPT-4oInput Images=12026.06 | 91.14 | |
| RS-EoTModel Category=Open-source Reasoning Vision-Language Models2026.03 | 90.25 | |
| RemoteAgentPublication=-2026.04 | 90.23 | |
| Gemini-2.0-flashModel Category=Closed-source Commercial Vision-Language Models2026.03 | 90 | |
| EarthDialModel Category=Open-source Remote Sensing Vision-Language Models2026.03 | 88.76 | |
| Kimi-VL-ThinkingModel Category=Open-source Reasoning Vision-Language Models2026.03 | 88.68 | |
| GLM-4.1V-ThinkingModel Category=Open-source Reasoning Vision-Language Models2026.03 | 86.84 | |
| Qwen2.5-VLModel Category=Open-source Vision-Language Models2026.03 | 86.05 | |
| GeoChatPublication=CVPR’242026.04 | 84.8 | |
| GeoChat (7B)Input Images=12026.06 | 80.09 | |
| InternVL2 (8B)Input Images=12026.06 | 79.3 | |
| Qwen2.5-VL (3B)Input Images=12026.06 | 78.21 | |
| GeoMagPublication=MM’252026.04 | 77.62 | |
| Qwen2.5-VLPublication=arXiv’252026.04 | 76.6 | |
| Claude-sonnet-4Model Category=Closed-source Commercial Vision-Language Models2026.03 | 76.32 | |
| Phi3.5-VisionPublication=arXiv’242026.04 | 68.9 | |
| MiniGPT-v2Model Category=Open-source Vision-Language Models2026.03 | 30.79 |