Visual Spatial Reasoning on SpaceVista-Bench Outdoor
43ScoreGPT-5
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-5Model Category=Closed-sourced Commercial Models, Instruction-tuned=true, Resolution=Same, FPS=Same2025.10 | 43 | |
| SpaceVista-7bModel Category=Open-Source Specialized Models, Instruction-tuned=true, Resolution=Same, FPS=Same2025.10 | 39.1 | |
| GPT-4oModel Category=Closed-sourced Commercial Models, Instruction-tuned=true, Resolution=Same, FPS=Same2025.10 | 38.3 | |
| Internvl3-38BModel Category=Open-Source General Models, Instruction-tuned=true, Resolution=Same, FPS=Same2025.10 | 38 | |
| Claude-Sonnet-4Model Category=Closed-sourced Commercial Models, Instruction-tuned=true, Resolution=Same, FPS=Same2025.10 | 34.1 | |
| Qwen2.5VL-32BModel Category=Open-Source General Models, Instruction-tuned=true, Resolution=Same, FPS=Same2025.10 | 30.7 | |
| Internvl3-78BModel Category=Open-Source General Models, Instruction-tuned=true, Resolution=Same, FPS=Same2025.10 | 30.3 | |
| Claude-Opus-4.1Model Category=Closed-sourced Commercial Models, Instruction-tuned=true, Resolution=Same, FPS=Same2025.10 | 30 | |
| Gemini-2.5-proModel Category=Closed-sourced Commercial Models, Instruction-tuned=true, Resolution=Same, FPS=Same2025.10 | 29 | |
| Qwen2.5VL-72BModel Category=Open-Source General Models, Instruction-tuned=true, Resolution=Same, FPS=Same2025.10 | 28 | |
| Internvl3.5-38BModel Category=Open-Source General Models, Instruction-tuned=true, Resolution=Same, FPS=Same2025.10 | 27 | |
| Gemini-2.5-flashModel Category=Closed-sourced Commercial Models, Instruction-tuned=true, Resolution=Same, FPS=Same2025.10 | 26.9 | |
| VLM-3RModel Category=Open-Source Specialized Models, Instruction-tuned=true, Resolution=Same, FPS=Same2025.10 | 26.9 | |
| GLM-4.5VModel Category=Open-Source General Models, Instruction-tuned=true, Resolution=Same, FPS=Same2025.10 | 25.2 | |
| Internvl3.5-14BModel Category=Open-Source General Models, Instruction-tuned=true, Resolution=Same, FPS=Same2025.10 | 24.3 | |
| Spatial-MLLMModel Category=Open-Source Specialized Models, Instruction-tuned=true, Resolution=Same, FPS=Same2025.10 | 23.1 | |
| SpaceRModel Category=Open-Source Specialized Models, Instruction-tuned=true, Resolution=Same, FPS=Same2025.10 | 19.8 | |
| GLM-4.1V-ThinkingModel Category=Open-Source General Models, Instruction-tuned=true, Resolution=Same, FPS=Same2025.10 | 13.3 | |
| LLAVA-Onevision-72BModel Category=Open-Source General Models, Instruction-tuned=true, Resolution=Same, FPS=Same2025.10 | 11.7 | |
| LLAVA-Onevision-7BModel Category=Open-Source General Models, Instruction-tuned=true, Resolution=Same, FPS=Same2025.10 | 11.6 |