Visual Question Answering on Spatial Reasoning Average
81.4AccuracySandboxVLM
Evaluation results
| Method | Links | |
|---|---|---|
| SandboxVLMMethod Category=Test-time Scaling VLMs2025.11 | 81.4 | |
| RoboBrain2.0-32BMethod Category=Training-Based Models, Model Scale=32B2025.11 | 81 | |
| Gemini-2.5-ProMethod Category=Generalist VLMs2025.11 | 80.3 | |
| MindJourneyMethod Category=Test-time Scaling VLMs2025.11 | 79.1 | |
| GPT-5-miniMethod Category=Generalist VLMs2025.11 | 78.5 | |
| Qwen2.5-VL-32BMethod Category=Generalist VLMs, Model Scale=32B2025.11 | 77.5 | |
| Claude-Sonnet-4Method Category=Generalist VLMs2025.11 | 74 | |
| VeBrain-8BMethod Category=Training-Based Models, Model Scale=8B2025.11 | 72 | |
| Qwen2.5-VL-72BMethod Category=Generalist VLMs, Model Scale=72B2025.11 | 71.1 | |
| GPT-4oMethod Category=Generalist VLMs2025.11 | 71 | |
| Magma-8BMethod Category=Training-Based Models, Model Scale=8B2025.11 | 66.9 | |
| Cosmos-Reason1Method Category=Training-Based Models2025.11 | 65.6 |