Scene Classification on UCMerced
98.63AccuracyRS Agent
Evaluation results
| Method | Links | |
|---|---|---|
| RS Agent2024.06 | 98.63 | |
| LHRS-Bot2024.06 | 96.63 | |
| EarthDial (4B)Input Images=12026.06 | 92.42 | |
| GeoSolverModel Category=Ours2026.03 | 92.38 | |
| Earth-OneVision (2B)Input Images=12026.06 | 91.83 | |
| VHMModel Category=Open-source Remote Sensing Vision-Language Models2026.03 | 89.29 | |
| VHM (7B)Input Images=12026.06 | 89.29 | |
| GPT-4oInput Images=12026.06 | 88.76 | |
| ChatGPT-5Model Category=Closed-source Commercial Vision-Language Models2026.03 | 88.57 | |
| Gemini-2.0-flashModel Category=Closed-source Commercial Vision-Language Models2026.03 | 85.95 | |
| RS-EoTModel Category=Open-source Reasoning Vision-Language Models2026.03 | 85.95 | |
| SkySenseGPTModel Category=Open-source Remote Sensing Vision-Language Models2026.03 | 85 | |
| SkySenseGPT (7B)Input Images=12026.06 | 85 | |
| GeoChat (7B)Input Images=12026.06 | 84.43 | |
| GeoChat2024.06 | 84.43 | |
| GLM-4.1V-ThinkingModel Category=Open-source Reasoning Vision-Language Models2026.03 | 82.86 | |
| EarthDialModel Category=Open-source Remote Sensing Vision-Language Models2026.03 | 80.71 | |
| Qwen2.5-VLModel Category=Open-source Vision-Language Models2026.03 | 78.33 | |
| Kimi-VL-ThinkingModel Category=Open-source Reasoning Vision-Language Models2026.03 | 77.62 | |
| LLaVA-1.52024.06 | 68 | |
| Claude-sonnet-4Model Category=Closed-source Commercial Vision-Language Models2026.03 | 67.86 | |
| MiniGPTv22024.06 | 62.9 | |
| Qwen-VL-Chat2024.06 | 62.9 | |
| Qwen2.5-VL (3B)Input Images=12026.06 | 60.86 | |
| InternVL2 (8B)Input Images=12026.06 | 58.23 | |
| MiniGPT-v2Model Category=Open-source Vision-Language Models2026.03 | 32.86 |