Remote Sensing Classification on SIRI-WHU
78.88Top-1 AccRS-EoT
Evaluation Results
| Method | Links | |
|---|---|---|
| RS-EoTModel Category=Open-source Reasoning Vision-Language Models2026.03 | 78.88 | |
| GeoSolverModel Category=Ours2026.03 | 76 | |
| ChatGPT-5Model Category=Closed-source Commercial Vision-Language Models2026.03 | 75 | |
| EarthDialModel Category=Open-source Remote Sensing Vision-Language Models2026.03 | 73.42 | |
| RemoteCLIPARCH=ViT-L/14, Zero-shot=true, Approach=Meta-prompting (LLaMA-3.1)2026.06 | 72.6 | |
| Gemini-2.0-flashModel Category=Closed-source Commercial Vision-Language Models2026.03 | 72 | |
| VHMLLM=Vicuna-1.5-7B2025.12 | 70.88 | |
| Kimi-VL-ThinkingModel Category=Open-source Reasoning Vision-Language Models2026.03 | 69 | |
| RemoteCLIPARCH=ViT-B/32, Zero-shot=true, Approach=Meta-prompting (LLaMA-3.1)2026.06 | 68.3 | |
| Qwen2.5-VLModel Category=Open-source Vision-Language Models2026.03 | 67.33 | |
| MF-RSVLMLLM=Vicuna-1.5-7B2025.12 | 67.29 | |
| RemoteCLIPArchitecture=ViT-L/14, Setting=Zero-shot, Template=DST2026.06 | 67 | |
| MetaCLIP-2.5BArchitecture=ViT-B/16, Setting=Zero-shot, Template=DST2026.06 | 66.8 | |
| InternVL3.5LLM=InternVL3.52025.12 | 66.67 | |
| CLIP LAION-RSArchitecture=ViT-L/14, Setting=Zero-shot, Template=DST2026.06 | 66.6 | |
| MetaCLIP-400MArchitecture=ViT-L/14, Setting=Zero-shot, Template=DST2026.06 | 66.5 | |
| SkyCLIPArchitecture=ViT-L/14, Setting=Zero-shot, Template=DST2026.06 | 66.5 | |
| MetaCLIP-2.5BArchitecture=ViT-L/14, Setting=Zero-shot, Template=DST2026.06 | 65.8 | |
| CLIPArchitecture=ViT-L/14, Setting=Zero-shot, Template=DST2026.06 | 65.2 | |
| Claude-sonnet-4Model Category=Closed-source Commercial Vision-Language Models2026.03 | 64.33 | |
| VHMModel Category=Open-source Remote Sensing Vision-Language Models2026.03 | 64.33 | |
| RemoteCLIPArchitecture=ViT-B/32, Setting=Zero-shot, Template=DST2026.06 | 63.9 | |
| GeoRSCLIPArchitecture=ViT-L/14, Setting=Zero-shot, Template=DST2026.06 | 63.7 | |
| SigLIPArchitecture=ViT-L/16, Setting=Zero-shot, Template=DST2026.06 | 63.1 | |
| SigLIP2Architecture=ViT-L/16, Setting=Zero-shot, Template=DST2026.06 | 62.9 | |
| LHRS-BotLLM=LLaMA-2-7B2025.12 | 62.66 | |
| MetaCLIP-400MARCH=ViT-L/14, Zero-shot=true, Approach=Meta-prompting (LLaMA-3.1)2026.06 | 62.6 | |
| SigLIPArchitecture=ViT-B/16, Setting=Zero-shot, Template=DST2026.06 | 62.5 | |
| MetaCLIP-2.5BARCH=ViT-L/14, Zero-shot=true, Approach=Meta-prompting (LLaMA-3.1)2026.06 | 62.3 | |
| Qwen2.5-VLLLM=Qwen2.5-7B2025.12 | 61.54 | |
| MiniCPM-V-2.6LLM=Qwen2-7B2025.12 | 61.5 | |
| GeoRSCLIPARCH=ViT-L/14, Zero-shot=true, Approach=Meta-prompting (LLaMA-3.1)2026.06 | 61.1 | |
| SkyCLIPARCH=ViT-L/14, Zero-shot=true, Approach=Meta-prompting (LLaMA-3.1)2026.06 | 61.1 | |
| CLIP LAION-RSARCH=ViT-L/14, Zero-shot=true, Approach=Meta-prompting (LLaMA-3.1)2026.06 | 60.8 | |
| GeoRSCLIPARCH=ViT-B/32, Zero-shot=true, Approach=Meta-prompting (LLaMA-3.1)2026.06 | 60.6 | |
| MetaCLIP-400MArchitecture=ViT-B/16, Setting=Zero-shot, Template=DST2026.06 | 60.5 | |
| SigLIP2Architecture=ViT-B/16, Setting=Zero-shot, Template=DST2026.06 | 60.5 | |
| EarthDialLLM=Phi-3-mini2025.12 | 60.42 | |
| SigLIP2ARCH=ViT-L/16, Zero-shot=true, Approach=Meta-prompting (LLaMA-3.1)2026.06 | 60.4 | |
| GLM-4.1V-ThinkingModel Category=Open-source Reasoning Vision-Language Models2026.03 | 60.33 | |
| GeoRSCLIPArchitecture=ViT-B/32, Setting=Zero-shot, Template=DST2026.06 | 60.3 | |
| SigLIPARCH=ViT-L/16, Zero-shot=true, Approach=Meta-prompting (LLaMA-3.1)2026.06 | 58.3 | |
| MetaCLIP-400MARCH=ViT-B/16, Zero-shot=true, Approach=Meta-prompting (LLaMA-3.1)2026.06 | 57.9 | |
| CLIPARCH=ViT-L/14, Zero-shot=true, Approach=Meta-prompting (LLaMA-3.1)2026.06 | 57.8 | |
| InternVL2.5LLM=InternLM-2.52025.12 | 57.67 | |
| MetaCLIP-2.5BARCH=ViT-B/16, Zero-shot=true, Approach=Meta-prompting (LLaMA-3.1)2026.06 | 57.3 | |
| SigLIP2ARCH=ViT-B/16, Zero-shot=true, Approach=Meta-prompting (LLaMA-3.1)2026.06 | 57.2 | |
| SigLIPARCH=ViT-B/16, Zero-shot=true, Approach=Meta-prompting (LLaMA-3.1)2026.06 | 55.6 | |
| SkySenseGPTModel Category=Open-source Remote Sensing Vision-Language Models2026.03 | 55.33 | |
| CLIPArchitecture=ViT-B/16, Setting=Zero-shot, Template=DST2026.06 | 55.3 | |
| mPLUG-OWL2LLM=LLaMA-2-7B2025.12 | 54.83 | |
| RemoteCLIPARCH=RN-50, Zero-shot=true, Approach=Meta-prompting (LLaMA-3.1)2026.06 | 54.7 | |
| Qwen-VLLLM=Qwen-7B2025.12 | 54.58 | |
| RemoteCLIPArchitecture=RN-50, Setting=Zero-shot, Template=DST2026.06 | 54 | |
| GeoChatLLM=Vicuna-1.5-7B2025.12 | 53.17 | |
| CLIPARCH=ViT-B/16, Zero-shot=true, Approach=Meta-prompting (LLaMA-3.1)2026.06 | 52.9 | |
| InternLM-XComposeLLM=InternLM-7B2025.12 | 46.83 | |
| Phi-3.5-VisionLLM=Phi-3.52025.12 | 40.42 | |
| MiniGPTv2LLM=LLaMA-2-7B2025.12 | 35.46 | |
| MiniGPT-v2Model Category=Open-source Vision-Language Models2026.03 | 26.67 | |
| InstructBLIPLLM=Vicuna-7B2025.12 | 18.2 | |
| LLaVA-1.5LLM=Vicuna-1.5-7B2025.12 | 17.71 |